Recent advances in large language models (LLMs) have broadened their applicability across diverse tasks, yet specialized domains still require targeted post-training. Among existing methods, Group Relative Policy Optimization (GRPO) stands out for its efficiency, leveraging groupwise relative rewards while avoiding costly value function learning. However, GRPO treats candidate responses as independent, overlooking semantic interactions such as complementarity and contradiction. To address this challenge, we first introduce a Structural Causal Model (SCM) that reveals hidden dependencies among candidate responses induced by conditioning on a final integrated output, forming a collider structure. Then, our causal analysis leads to two insights: (1) projecting responses onto a causally-informed subspace improves prediction quality, and (2) this projection yields a better baseline than query-only conditioning. Building on these insights, we propose Group Causal Policy Optimization (GCPO), which integrates causal structure into optimization through two key components: a causally-informed reward adjustment and a novel KL-regularization term that aligns the policy with a causally-projected reference distribution. Comprehensive experimental evaluations on various benchmarks demonstrate that GCPO consistently surpasses existing methods.

In this paper, we explore the transferability of SSL by addressing two central questions: (i) what is the representation transferability of SSL, and (ii) how can we effectively model this transferability? Transferability is defined as the ability of a representation learned from one task to support the objective of another. Inspired by the meta-learning paradigm, we construct multiple SSL tasks within each training batch to support explicitly modeling transferability. Based on empirical evidence and causal analysis, we find that although introducing task-level information improves transferability, it is still hindered by task conflict. To address this issue, we propose a Task Conflict Calibration method to alleviate the impact of task conflict. Specifically, it first splits batches to create multiple SSL tasks, infusing task-level information. Next, it uses a factor extraction network to produce causal generative factors for all tasks and a weight extraction network to assign dedicated weights to each sample, employing data reconstruction, orthogonality, and sparsity to ensure effectiveness. Finally, the method calibrates sample representations during SSL training and integrates into the pipeline via a two-stage bi-level optimization framework to boost the transferability of learned representations. Experimental results on multiple downstream tasks demonstrate that our method consistently improves the transferability of SSL models.

Graph contrastive learning (GCL) aims to learn discriminative semantic invariance by contrasting different views of the same graph that share critical topological patterns. However, existing GCL approaches with structural augmentations often struggle to identify task-relevant topological structures, let alone adapt to the varying coarse-to-fine topological granularities required across different downstream tasks. To remedy this issue, we introduce Hierarchical Topological Granularity Graph Contrastive Learning (HTG-GCL), a novel framework that leverages transformations of the same graph to generate multi-scale ring-based cellular complexes, embodying the concept of topological granularity, thereby generating diverse topological views. Recognizing that a certain granularity may contain misleading semantics, we propose a multi-granularity decoupled contrast and apply a granularity-specific weighting mechanism based on uncertainty estimation. Comprehensive experiments on various benchmarks demonstrate the effectiveness of HTG-GCL, highlighting its superior performance in capturing meaningful graph representations through hierarchical topological information.

Test-time prompt tuning for vision-language models has demonstrated impressive generalization capabilities under zero-shot settings. However, tuning the learnable prompts solely based on unlabeled test data may induce prompt optimization bias, ultimately leading to suboptimal performance on downstream tasks. In this work, we analyze the underlying causes of prompt optimization bias from both the model and data perspectives. In terms of the model, the entropy minimization objective typically focuses on reducing the entropy of model predictions while overlooking their correctness. This can result in overconfident yet incorrect outputs, thereby compromising the quality of prompt optimization. On the data side, prompts affected by optimization bias can introduce misalignment between visual and textual modalities, which further aggravates the prompt optimization bias. To this end, we propose a Doubly Debiased Test-Time Prompt Tuning method, abbreviated as D2TPT. Specifically, we first introduce a dynamic retrieval-augmented modulation module that retrieves high-confidence knowledge from a dynamic knowledge base using the test image feature as a query, and uses the retrieved knowledge to modulate the predictions. Guided by the refined predictions, we further develop a reliability-aware prompt optimization module that incorporates a confidence-based weighted ensemble and cross-modal consistency distillation to impose regularization constraints during prompt tuning. Extensive experiments across 15 benchmark datasets involving both natural distribution shifts and cross-datasets generalization demonstrate that D2TPT outperforms baselines, validating its effectiveness in mitigating prompt optimization bias.

Exploration in sparse-reward tasks remains a fundamental challenge in multi-agent reinforcement learning (MARL) due to complex inter-agent interactions and the expansive exploration space. To address this issue, we propose Targeted Multi-Agent Exploration (TMAE), a novel framework that uncovers the causal relationships between the state space and the reward function, thereby reducing the exploration space and enabling more targeted exploration. Specifically, we construct a structural causal model (SCM) to model the causality between sub-state variables and sparse rewards, providing a robust analytical foundation for subsequent causal inference. Through counterfactual causal intervention, TMAE identifies the most critical subspaces for discovering rare but pivotal events while filtering out confounders. By incorporating these causal insights into the exploration process, TMAE prioritizes subspaces with stronger causal effects on sparse rewards, significantly enhancing exploration efficiency. We evaluate TMAE on a range of MARL benchmarks featuring sparse rewards, consistently demonstrating superior exploration efficiency compared to state-of-the-art methods. Furthermore, visualized causal insights derived from TMAE reveal its ability to effectively capture intricate dependencies and priorities in targeted exploration, showcasing strong alignment with prior domain knowledge.

The World Wide Web needs reliable predictive capabilities to respond to changes in user behavior and usage patterns. Time series forecasting (TSF) is a key means to achieve this goal. In recent years, the large language models (LLMs) for TSF (LLM4TSF) have achieved good performance. However, there is a significant difference between pretraining corpora and time series data, making it hard to guarantee forecasting quality when directly applying LLMs to TSF; fine-tuning LLMs can mitigate this issue, but often incurs substantial computational overhead. Thus, LLM4TSF faces a dual challenge of prediction performance and compute overhead. To address this, we aim to explore a method for improving the forecasting performance of LLM4TSF while freezing all LLM parameters to reduce computational overhead. Inspired by in-context learning (ICL), we propose LVICL. LVICL uses our vector-injected ICL to inject example information into a frozen LLM, eliciting its in-context learning ability and thereby enhancing its performance on the example-related task (i.e., TSF). Specifically, we first use the LLM together with a learnable context vector adapter to extract a context vector from multiple examples adaptively. This vector contains compressed, example-related information. Subsequently, during the forward pass, we inject this vector into every layer of the LLM to improve forecasting performance. Compared with conventional ICL that adds examples into the prompt, our vector-injected ICL does not increase prompt length; moreover, adaptively deriving a context vector from examples suppresses components harmful to forecasting, thereby improving model performance. Extensive experiments demonstrate the effectiveness of our approach.

In this paper, we addressed the limitation of relying solely on distribution alignment and source-domain empirical risk minimization in Unsupervised Domain Adaptation (UDA). Our information-theoretic analysis showed that this standard adversarial-based framework neglects the discriminability of target-domain features, leading to suboptimal performance. To bridge this theoretical-practical gap, we defined "good representation learning" as guaranteeing both transferability and discriminability, and proved that an additional loss term targeting target-domain discriminability is necessary. Building on these insights, we proposed a novel adversarial-based UDA framework that explicitly integrates a domain alignment objective with a discriminability-enhancing constraint. Instantiated as Domain-Invariant Representation Learning with Global and Local Consistency (RLGLC), our method leverages Asymmetrically-Relaxed Wasserstein of Wasserstein Distance (AR-WWD) to address class imbalance and semantic dimension weighting, and employs a local consistency mechanism to preserve fine-grained target-domain discriminative information. Extensive experiments across multiple benchmark datasets demonstrate that RLGLC consistently surpasses state-of-the-art methods, confirming the value of our theoretical perspective and underscoring the necessity of enforcing both transferability and discriminability in adversarial-based UDA.

Graph representation learning methods are highly effective in handling complex non-Euclidean data by capturing intricate relationships and features within graph structures. However, traditional methods face challenges when dealing with heterogeneous graphs that contain various types of nodes and edges due to the diverse sources and complex nature of the data. Existing heterogeneous graph neural networks (HGNNs) have shown promising results but require prior knowledge of node and edge types and unified node feature formats, which limits their applicability. Recent advancements in graph representation learning using large language models (LLMs) offer new solutions by integrating LLMs' data processing capabilities, enabling the alignment of various graph representations. Nevertheless, these methods often overlook heterogeneous graph data and require extensive preprocessing. To address these limitations, we propose an LLM-enhanced Heterogeneous Graph Neural Network (LHGNN). LHGNN leverages the strengths of both LLM and GNN, allowing for the processing of graph data with any format and type of nodes and edges without the need for type information or special preprocessing. LHGNN employs LLM to automatically summarize and classify different data formats and types, aligns node features, and uses a specialized GNN for targeted learning, thus obtaining effective graph representations for downstream tasks. Theoretical analysis and experimental validation have demonstrated the effectiveness of our method.

Multimodal knowledge graphs (KGs) have found widespread applications in data integration and processing, yet existing multimodal knowledge graphs are often highly incomplete, which impedes their wide adoption. Thereby multimodal knowledge graph completion (MKGC) has attracted widespread attention. However, the heterogeneity of multiple modalities degenerates the representations’ capacity to model modalityshared discriminative knowledge. The state-of-the-art approach addresses this challenge by aligning the modality distributions by adopting a Sinkhorn-based approach, but such an approach is computationally expensive and the practical sampling strategy largely degrades the model performance. Therefore we propose the augmented modality distribution alignment module, which imposes the generalized Radon transform-based approach to perform efficient and accurate distribution alignment. Yet the alignment may result in undesirable instance-level feature structure disorder. We thus propose the relation-aware instance preserving module. Empirical comparisons on well-established MKGC benchmarks demonstrate the effectiveness of proposed method.

Scene recognition, particularly for aerial and underwater images, often suffers from various types of degradation, such as blurring or overexposure. Previous works that focus on convolutional neural networks have been shown to be able to extract panoramic semantic features and perform well on scene recognition tasks. However, low-quality images still impede model performance due to the inappropriate use of high-level semantic features. To address these challenges, we propose an adaptive selection mechanism to identify the most important and robust regions with high-level features. Thus, the model can perform learning via these regions to avoid interference. implement a learnable mask in the neural network, which can filter high-level features by assigning weights to different regions of the feature matrix. We also introduce a regularization term to further enhance the significance of key high-level feature regions. Different from previous methods, our learnable matrix pays extra attention to regions that are important to multiple categories but may cause misclassification and sets constraints to reduce the influence of such regions. This is a plug-and-play architecture that can be easily extended to other methods. Additionally, we construct an Underwater Geological Scene Classification dataset to assess the effectiveness of our model. Extensive experimental results demonstrate the superiority and robustness of our proposed method over state-of-the-art techniques on two datasets.

The use of large language models (LLMs) as feature enhancers to optimize node representations, which are then used as inputs for graph neural networks (GNNs), has shown significant potential in graph representation learning. However, the fundamental properties of this approach remain underexplored. To address this issue, we propose conducting a more in-depth analysis of this issue based on the interchange intervention method. First, we construct a synthetic graph dataset with controllable causal relationships, enabling precise manipulation of semantic relationships and causal modeling to provide data for analysis. Using this dataset, we conduct interchange interventions to examine the deeper properties of LLM enhancers and GNNs, uncovering their underlying logic and internal mechanisms. Building on the analytical results, we design a plug-and-play optimization module to improve the information transfer between LLM enhancers and GNNs. Experiments across multiple datasets and models validate the proposed module.

In this paper, we focus on the out-of-distribution (OOD) generalization of self-supervised learning (SSL). By analyzing the mini-batch construction during the SSL training phase, we first give one plausible explanation for SSL having OOD generalization. Then, from the perspective of data generation and causal inference, we analyze and conclude that SSL learns spurious correlations during the training process, which leads to a reduction in OOD generalization. To address this issue, we propose a post-intervention distribution (PID) grounded in the Structural Causal Model. PID offers a scenario where the spurious variable and label variable is mutually independent. Besides, we demonstrate that if each mini-batch during SSL training satisfies PID, the resulting SSL model can achieve optimal worst-case OOD performance. This motivates us to develop a batch sampling strategy that enforces PID constraints through the learning of a latent variable model. Through theoretical analysis, we demonstrate the identifiability of the latent variable model and validate the effectiveness of the proposed sampling strategy. Experiments conducted on various downstream OOD tasks demonstrate the effectiveness of the proposed sampling strategy.

Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, but its performance can degrade when fine-tuned in out-of-distribution (OOD) scenarios. We model the prediction process using a Structural Causal Model (SCM) and show that the causal mechanism involving both invariant and variant factors in training environments differs from that in test environments. In contrast, the causal mechanism with solely invariant factors remains consistent across environments. We theoretically prove the existence of a linear mapping from CLIP embeddings to invariant factors, which can be estimated using interventional data. Additionally, we provide a condition to guarantee low OOD risk of the invariant predictor. Based on these insights, we propose the Invariant Causal Mechanism of CLIP (CLIP-ICM) framework. CLIP-ICM involves collecting interventional data, estimating a linear projection matrix, and making predictions within the invariant subspace. Experiments on several OOD datasets show that CLIP-ICM significantly improves the performance of CLIP. Our method offers a simple but powerful enhancement, boosting the reliability of CLIP in real-world applications.

Multi-Modal Learning (MML) aims to learn effective representations across modalities for accurate predictions. Existing methods typically focus on modality consistency and specificity to learn effective representations. However, from a causal perspective, they may lead to representations that contain insufficient and unnecessary information. To address this, we propose that effective MML representations should be causally sufficient and necessary. Considering practical issues like spurious correlations and modality conflicts, we relax the exogeneity and monotonicity assumptions prevalent in prior works and explore the concepts specific to MML, i.e., Causal Complete Cause ($C^3$). We begin by defining $C^3$, which quantifies the probability of representations being causally sufficient and necessary. We then discuss the identifiability of $C^3$ and introduce an instrumental variable to support identifying $C^3$ with non-exogeneity and non-monotonicity. Building on this, we conduct the $C^3$ measurement, i.e., $C^3$ risk. We propose a twin network to estimate it through (i) the real-world branch: utilizing the instrumental variable for sufficiency, and (ii) the hypothetical-world branch: applying gradient-based counterfactual modeling for necessity. Theoretical analyses confirm its reliability. Based on these results, we propose $C^3$ Regularization, a plug-and-play method that enforces the causal completeness of the learned representations by minimizing $C^3$ risk. Extensive experiments demonstrate its effectiveness.

Large Language Models (LLMs) have achieved remarkable success across various domains. However, they still face significant challenges, including high computational costs for training and limitations in solving complex reasoning problems. Although existing methods have extended the reasoning capabilities of LLMs through structured paradigms, these approaches often rely on task-specific prompts and predefined reasoning processes, which constrain their flexibility and generalizability. To address these limitations, we propose a novel framework that leverages graph learning to enable more flexible and adaptive reasoning capabilities for LLMs. Specifically, this approach models the reasoning process of a problem as a graph and employs LLM-based graph learning to guide the adaptive generation of each reasoning step. To further enhance the adaptability of the model, we introduce a Graph Neural Network (GNN) module to perform representation learning on the generated reasoning process, enabling real-time adjustments to both the model and the prompt. Experimental results demonstrate that this method significantly improves reasoning performance across multiple tasks without requiring additional training or task-specific prompt design. Code can be found in https://github.com/zch65458525/L2T.

Scene understanding is one of the core tasks in computer vision, aiming to extract semantic information from images to identify objects, scene categories, and their interrelationships. Although advancements in Vision-Language Models (VLMs) have driven progress in this field, existing VLMs still face challenges in adaptation to unseen complex wide-area scenes. To address the challenges, this paper proposes a Hierarchical Coresets Selection (HCS) mechanism to advance the adaptation of VLMs in complex wide-area scene understanding. It progressively refines the selected regions based on the proposed theoretically guaranteed importance function, which considers utility, representativeness, robustness, and synergy. Without requiring additional fine-tuning, HCS enables VLMs to achieve rapid understandings of unseen scenes at any scale using minimal interpretable regions while mitigating insufficient feature density. HCS is a plug-and-play method that is compatible with any VLM. Experiments demonstrate that HCS achieves superior performance and universality in various tasks. The code is available at https://wangjingyao07.github.io/HCS.github.io/.

Large language models (LLMs) excel at complex tasks thanks to advances in their reasoning abilities. However, existing methods overlook the trade-off between reasoning effectiveness and efficiency, often encouraging unnecessarily long reasoning chains and wasting tokens. To address this, we propose Learning to Think (L2T), an information-theoretic reinforcement fine-tuning framework for LLMs to make the models achieve optimal reasoning with fewer tokens. Specifically, L2T treats each query-response interaction as a hierarchical session of multiple episodes and proposes a universal dense process reward, i.e., quantifies the episode-wise information gain in parameters, requiring no extra annotations or task-specific evaluators. We propose a method to quickly estimate this reward based on PAC-Bayes bounds and the Fisher information matrix. Theoretical analyses show that it significantly reduces computational complexity with high estimation accuracy. By immediately rewarding each episode's contribution and penalizing excessive updates, L2T optimizes the model via reinforcement learning to maximize the use of each episode and achieve effective updates. Empirical results on various reasoning benchmarks and base models demonstrate the advantage of L2T across different tasks, boosting both reasoning effectiveness and efficiency.

Freeform handwriting authentication verifies a person's identity from their writing style and habits in messy handwriting data. This technique has gained widespread attention in recent years as a valuable tool for various fields, e.g., fraud prevention and cultural heritage protection. However, it still remains a challenging task in reality due to three reasons: (i) severe damage, (ii) complex high-dimensional features, and (iii) lack of supervision. To address these issues, we propose SherlockNet, an energy-oriented two-branch contrastive self-supervised learning framework for robust and fast freeform handwriting authentication. It consists of four stages: (i) pre-processing: converting manuscripts into energy distributions using a novel plug-and-play energy-oriented operator to eliminate the influence of noise; (ii) generalized pre-training: learning general representation through two-branch momentum-based adaptive contrastive learning with the energy distributions, which handles the high-dimensional features and spatial dependencies of handwriting; (iii) personalized fine-tuning: calibrating the learned knowledge using a small amount of labeled data from downstream tasks; and (iv) practical application: identifying individual handwriting from scrambled, missing, or forged data efficiently and conveniently. Considering the practicality, we construct EN-HA, a novel dataset that simulates data forgery and severe damage in real applications. Finally, we conduct extensive experiments on six benchmark datasets including our EN-HA, and the results prove the robustness and efficiency of SherlockNet.

Graph Neural Networks (GNNs) demonstrate their significance by effectively modeling complex interrelationships within graph-structured data. To enhance the credibility and robustness of GNNs, it becomes exceptionally crucial to bolster their ability to capture causal relationships. However, despite recent advancements that have indeed strengthened GNNs from a causal learning perspective, conducting an in-depth analysis specifically targeting the causal modeling prowess of GNNs remains an unresolved issue. In order to comprehensively analyze various GNN models from a causal learning perspective, we constructed an artificially synthesized dataset with known and controllable causal relationships between data and labels. The rationality of the generated data is further ensured through theoretical foundations. Drawing insights from analyses conducted using our dataset, we introduce a lightweight and highly adaptable GNN module designed to strengthen GNNs' causal learning capabilities across a diverse range of tasks. Through a series of experiments conducted on both synthetic datasets and other real-world datasets, we empirically validate the effectiveness of the proposed module. The codes are available at https://github.com/yaoyao-yaoyao-cell/CRCG.

Graph contrastive learning is a general learning paradigm excelling at capturing invariant information from diverse perturbations in graphs. Recent works focus on exploring the structural rationale from graphs, thereby increasing the discriminability of the invariant information. However, such methods may incur in the mis-learning of graph models towards the interpretability of graphs, and thus the learned noisy and task-agnostic information interferes with the prediction of graphs. To this end, with the purpose of exploring the intrinsic rationale of graphs, we accordingly propose to capture the dimensional rationale from graphs, which has not received sufficient attention in the literature. The conducted exploratory experiments attest to the feasibility of the aforementioned roadmap. To elucidate the innate mechanism behind the performance improvement arising from the dimensional rationale, we rethink the dimensional rationale in graph contrastive learning from a causal perspective and further formalize the causality among the variables in the pre-training stage to build the corresponding structural causal model. On the basis of the understanding of the structural causal model, we propose the dimensional rationale-aware graph contrastive learning approach, which introduces a learnable dimensional rationale acquiring network and a redundancy reduction constraint. The learnable dimensional rationale acquiring network is updated by leveraging a bi-level meta-learning technique, and the redundancy reduction constraint disentangles the redundant features through a decorrelation process during learning. Empirically, compared with state-of-the-art methods, our method can yield significant performance boosts on various benchmarks with respect to discriminability and transferability. The code implementation of our method is available at https://github.com/ByronJi/DRGCL.

Graph contrastive learning (GCL) aims to align the positive features while differentiating the negative features in the latent space by minimizing a pair-wise contrastive loss. As the embodiment of an outstanding discriminative unsupervised graph representation learning approach, GCL achieves impressive successes in various graph benchmarks. However, such an approach falls short of recognizing the topology isomorphism of graphs, resulting in that graphs with relatively homogeneous node features cannot be sufficiently discriminated. By revisiting classic graph topology recognition works, we disclose that the corresponding expertise intuitively complements GCL methods. To this end, we propose a novel hierarchical topology isomorphism expertise embedded graph contrastive learning, which introduces knowledge distillations to empower GCL models to learn the hierarchical topology isomorphism expertise, including the graph-tier and subgraph-tier. On top of this, the proposed method holds the feature of plug-and-play, and we empirically demonstrate that the proposed method is universal to multiple state-of-the-art GCL models. The solid theoretical analyses are further provided to prove that compared with conventional GCL methods, our method acquires the tighter upper bound of Bayes classification error. We conduct extensive experiments on real-world benchmarks to exhibit the performance superiority of our method over candidate GCL methods, e.g., for the real-world graph representation learning experiments, the proposed method beats the state-of-the-art method by 0.23% on unsupervised representation learning setting, 0.43% on transfer learning setting. Our code is available at https://github.com/jyf123/HTML.

Communication stands as a potent mechanism to harmonize the behaviors of multiple agents. However, existing work primarily concentrates on broadcast communication, which not only lacks practicality, but also leads to information redundancy. This surplus, one-fits-all information could adversely impact the communication efficiency. Furthermore, existing works often resort to basic mechanisms to integrate observed and received information, impairing the learning process. To tackle these difficulties, we propose Targeted and Trusted Multi-Agent Communication (T2MAC), a straightforward yet effective method that enables agents to learn selective engagement and evidence-driven integration. With T2MAC, agents have the capability to craft individualized messages, pinpoint ideal communication windows, and engage with reliable partners, thereby refining communication efficiency. Following the reception of messages, the agents integrate information observed and received from different sources at an evidence level. This process enables agents to collectively use evidence garnered from multiple perspectives, fostering trusted and cooperative behaviors. We evaluate our method on a diverse set of cooperative multi-agent tasks, with varying difficulties, involving different scales and ranging from Hallway, MPE to SMAC. The experiments indicate that the proposed model not only surpasses the state-of-the-art methods in terms of cooperative performance and communication efficiency, but also exhibits impressive generalization.

Marine radar is employed across multiple fields, notably in navigation, meteorology, defense, and security. Marine radar images are highly sensitive to sea clutter, highlighting the crucial importance of sea clutter suppression in radar image processing. However, existing algorithms for sea clutter suppression often struggle to effectively generalize in complex marine environments. In this paper, we introduce RadarDiff, a novel approach that leverages diffusion models to enhance sea clutter suppression in marine radar plan-position indicator (PPI) images. We treat sea clutter suppression as an image-to-image translation task and propose a novel data augmentation method to create image pairs with and without sea clutter. Additionally, we introduce a unique loss function designed to address the challenge of small targets disappearing after suppression. To our knowledge, we are the first to utilize the diffusion-based model in sea clutter suppression for radar PPI images. Our quantitative and qualitative results demonstrate significant improvements compared to traditional denoising methods and classical GAN-based models.

As a novel and effective fine-tuning paradigm based on large-scale pre-trained language models (PLMs), prompt-tuning aims to reduce the gap between downstream tasks and pre-training objectives. While prompt-tuning has yielded continuous advancements in various tasks, such an approach still remains a persistent defect: prompt-tuning methods fail to generalize to specific few-shot patterns. From the perspective of distribution analyses, we disclose that the intrinsic issues behind the phenomenon are the over-multitudinous conceptual knowledge contained in PLMs and the abridged knowledge for target downstream domains, which jointly result in that PLMs mis-locate the knowledge distributions corresponding to the target domains in the universal knowledge embedding space. To this end, we intuitively explore to approximate the unabridged target domains of downstream tasks in a debiased manner, and then abstract such domains to generate discriminative prompts, thereby providing the de-ambiguous guidance for PLMs. Guided by such an intuition, we propose a simple yet effective approach, namely BayesPrompt, to learn prompts that contain the domain discriminative information against the interference from domain-irrelevant knowledge. BayesPrompt primitively leverages known distributions to approximate the debiased factual distributions of target domains and further uniformly samples certain representative features from the approximated distributions to generate the ultimate prompts for PLMs. We provide theoretical insights with the connection to domain adaptation. Empirically, our method achieves state-of-the-art performance on benchmarks.

Diffusion Models are a potent class of generative models capable of producing high-quality images. However, they often inadvertently favor certain data attributes, undermining the diversity of generated images. This issue is starkly apparent in skewed datasets like CelebA, where the initial dataset disproportionately favors females over males by 57.9%, this bias amplified in generated data where female representation outstrips males by 148%. In response, we propose a plug-and-play method named Manifold Guidance Sampling, which is also the first unsupervised method to mitigate bias issue in DDPMs. Leveraging the inherent structure of the data manifold, this method steers the sampling process towards a more uniform distribution, effectively dispersing the clustering of biased data. Without the need for modifying the existing model or additional training, it significantly mitigates data bias and enhances the quality and unbiasedness of the generated images.

While generative adversarial networks have made significant strides in natural image synthesis, their performance in specialized remote sensing (RS) imagery, particularly in capturing fine details of small objects like airplanes and ships, needs enhancement. This deficiency frequently results in shape distortion within the generated images. This challenge, compounded by the prohibitive costs of annotating RS images, motivates the development of an efficient unsupervised approach. In response, this paper introduces Object-Aided Generative Adversarial Network (OAGAN), an innovative model for unsupervised RS image generation. Initially, it employs an object-centric learning mechanism to extract structural semantic maps of foreground objects, without the need for labels. Subsequently, this paper proposes the Shape Encoding Layer (SEL) to encode the structural semantics of objects, which is seamlessly integrated into the intermediate layers of the generative model. This integration enables the model to prioritize the structural information of foreground objects. Additionally, to enhance the diversity of generated images, this paper designs a novel style regularization term. Comprehensive experiments are conducted on three distinct RS image datasets. Experiment results demonstrate that the proposed method surpasses state-of-the-art models in terms of the quality of generated images.

Multi-modal recommendation aims at leveraging data of auxiliary modalities (e.g., linguistic descriptions and images) to enhance the representations of items, thereby accurately recommending items that users prefer from the vast expanse of Web-based data. Current multi-modal recommendation methods typically utilize multi-modal features to assist in learning item representations in a direct manner. However, the superfluous semantics in multi-modal features are ignored, resulting in the inclusion of excessive redundancy within the representations of items. Moreover, we disclose that multi-modal features of items rarely contain user-item interaction information. Hence, during the interaction among different item features, the user-item interaction information in ID-based representations diminishes, leading to the degeneration of recommendation performance. To this end, we propose a novel multi-modal recommendation approach, which compresses representations of extra modalities under the guidance of solid theoretical analysis and leverages two auxiliary multi-modal graphs to integrate user-item interaction information into multi-modal features. Empirical experiments on three multi-modal recommendation datasets demonstrate that our method outperforms benchmarks.

Long-term time series forecasting is a long-standing challenge in various applications. A central issue in time series forecasting is that methods should expressively capture long-term dependency. Furthermore, time series forecasting methods should be flexible when applied to different scenarios. Although Fourier analysis offers an alternative to effectively capture reusable and periodic patterns to achieve long-term forecasting in different scenarios, existing methods often assume high-frequency components represent noise and should be discarded in time series forecasting. However, we conduct a series of motivation experiments and discover that the role of certain frequencies varies depending on the scenarios. In some scenarios, removing high-frequency components from the original time series can improve the forecasting performance, while in others scenarios, removing them is harmful to forecasting performance. Therefore, it is necessary to treat the frequencies differently according to specific scenarios. To achieve this, we first reformulate the time series forecasting problem as learning a transfer function of each frequency in the Fourier domain. Further, we design Frequency Dynamic Fusion (FreDF), which individually predicts each Fourier component, and dynamically fuses the output of different frequencies. Moreover, we provide a novel insight into the generalization ability of time series forecasting and propose the generalization bound of time series forecasting. Then we prove FreDF has a lower bound, indicating that FreDF has better generalization ability. Extensive experiments conducted on multiple benchmark datasets and ablation studies demonstrate the effectiveness of FreDF.

When engaging in end-to-end graph representation learning with Graph Neural Networks (GNNs), the intricate causal relationships and rules inherent in graph data pose a formidable challenge for the model in accurately capturing authentic data relationships. A proposed mitigating strategy involves the direct integration of rules or relationships corresponding to the graph data into the model. However, within the domain of graph representation learning, the inherent complexity of graph data obstructs the derivation of a comprehensive causal structure that encapsulates universal rules or relationships governing the entire dataset. Instead, only specialized diminutive causal structures, delineating specific causal relationships within constrained subsets of graph data, emerge as discernible. Motivated by empirical insights, it is observed that GNN models exhibit a tendency to converge towards such specialized causal structures during the training process. Consequently, we posit that the introduction of these specific causal structures is advantageous for the training of GNN models. Building upon this proposition, we introduce a novel method that enables GNN models to glean insights from these specialized diminutive causal structures, thereby enhancing overall performance. Our method specifically extracts causal knowledge from the model representation of these diminutive causal structures and incorporates interchange intervention to optimize the learning process. Theoretical analysis serves to corroborate the efficacy of our proposed method. Furthermore, empirical experiments consistently demonstrate significant performance improvements across diverse datasets.

In recent years, there has been a prominent focus on enhancing the quality of features derived from convolutional neural networks (CNNs) within the field of polarimetric synthetic aperture radar (PolSAR) image classification. Targeting this challenge, this article first visualizes the lack of discriminability and generalizability in CNN features through several empirical observations. Subsequently, we explain why these problems arise from a causal perspective, accomplished by means of a structural causal model (SCM) constructed according to the training and testing process of CNNs. This SCM facilitates the identification of variables that affect the quality of PolSAR image feature learning, as well as an intervention on those variables using backdoor adjustment. Building upon this groundwork, a novel causal inference-guided feature enhancement framework is constructed. It can be seamlessly integrated into any CNN-based PolSAR image classifier in a plug-and-play manner, enabling the enhanced classifier to filter out interference information and prevent model overfitting. These two aspects bring better feature discriminability and generalizability, respectively, leading to improved classification performance. Experimental results on four widely-used PolSAR image datasets demonstrate the effectiveness of our proposed framework. We integrate it into several mainstream methods in the field and show that the accuracy of the enhanced classifier is improved compared to the original model.

Generative adversarial networks (GANs) have shown notable accomplishments in remote sensing (RS) domain. However, this article reveals that their performance on RS images falls short when compared to their impressive results with natural images. This study identifies a previously overlooked issue: GANs exhibit a heightened susceptibility to overfitting on RS images. To address this challenge, this article analyzes the characteristics of RS images and proposes manifold constraint regularization (MCR), a novel approach that tackles overfitting of GANs on RS images for the first time. Our method includes a new measure for evaluating the structure of the data manifold. Leveraging this measure, we propose the MCR term, which not only alleviates the overfitting problem, but also promotes alignment between the generated and real data manifolds, leading to enhanced quality in the generated images. The effectiveness and versatility of this method have been corroborated through extensive validation on various RS datasets and GAN models. The proposed method not only enhances the quality of the generated images, reflected in a 3.13% improvement in Fréchet inception distance (FID) score, but also boosts the performance of the GANs on downstream tasks, evidenced by a 3.76% increase in classification accuracy. The source code is available athttps://github.com/rootSue/Manifold-RSGAN.

The prevailing graph neural network models have achieved significant progress in graph representation learning. However, in this paper, we uncover an ever-overlooked phenomenon: the pre-trained graph representation learning model tested with full graphs underperforms the model tested with well-pruned graphs. This observation reveals that there exist confounders in graphs, which may interfere with the model learning semantic information, and current graph representation learning methods have not eliminated their influence. To tackle this issue, we propose Robust Causal Graph Representation Learning (RCGRL) to learn robust graph representations against confounding effects. RCGRL introduces an active approach to generate instrumental variables under unconditional moment restrictions, which empowers the graph representation learning model to eliminate confounders, thereby capturing discriminative information that is causally related to downstream predictions. We offer theorems and proofs to guarantee the theoretical effectiveness of the proposed approach. Empirically, we conduct extensive experiments on a synthetic dataset and multiple benchmark datasets. Experimental results demonstrate the effectiveness and generalization ability of RCGRL. Our codes are available at https://github.com/hang53/RCGRL.

Few-shot learning models learn representations with limited human annotations, and such a learning paradigm demonstrates practicability in various tasks, e.g., image classification, object detection, etc. However, few-shot object detection methods suffer from an intrinsic defect that the limited training data makes the model cannot sufficiently explore semantic information. To tackle this, we introduce knowledge distillation to the few-shot object detection learning paradigm. We further run a motivating experiment, which demonstrates that in the process of knowledge distillation, the empirical error of the teacher model degenerates the prediction performance of the few-shot object detection model as the student. To understand the reasons behind this phenomenon, we revisit the learning paradigm of knowledge distillation on the few-shot object detection task from the causal theoretic standpoint, and accordingly, develop a Structural Causal Model. Following the theoretical guidance, we propose a backdoor adjustment-based knowledge distillation method for the few-shot object detection task, namely Disentangle and Remerge (D&R), to perform conditional causal intervention toward the corresponding Structural Causal Model. Empirically, the experiments on benchmarks demonstrate that D&R can yield significant performance boosts in few-shot object detection. Code is available at https://github.com/ZYN-1101/DandR.git.

Abstract Compared with natural images, geospatial images cover larger area and have more complex image contents. There are few algorithms for generating controllable geospatial images, and their results are of low quality. In response to this problem, this paper proposes Geospatial Style Generative Adversarial Network to generate controllable and high‐quality geospatial images. Current conditional generators suffer the mode collapse problem in geospatial field. The problem is addressed via a modified mode seeking regularization term with contrastive learning theory. Besides, the discriminator network architecture is modified to process global feature information and texture information of geospatial images. Feature loss in the generator is introduced to stabilize the training process and improve generated image quality. Comprehensive experiments are conducted on UC Merced Land Use Dataset, NWPU‐RESISC45 Dataset, and AID Dataset to evaluate all compared methods. Experiment results show our method outperforms state‐of‐the‐art models. Our method not only generates high‐quality and controllable geospatial images, but also enhances the discriminator to learn better representations.

While self-supervised learning techniques are often used to mine hidden knowledge from unlabeled data via modeling multiple views, it is unclear how to perform effective representation learning in a complex and inconsistent context. To this end, we propose a new multi-view self-supervised learning method, namelyconsistency and complementarity network(CoCoNet), to comprehensively learn global inter-view consistent and local cross-view complementarity-preserving representations from multiple views. To capture crucial common knowledge which is implicitly shared among views, CoCoNet employs a global consistency module that aligns the probabilistic distribution of views by utilizing an efficient discrepancy metric based on the generalized sliced Wasserstein distance. To incorporate cross-view complementary information, CoCoNet proposes a heuristic complementarity-aware contrastive learning approach, which extracts a complementarity-factor jointing cross-view discriminative knowledge and uses it as the contrast to guide the learning of view-specific encoders. Theoretically, the superiority of CoCoNet is verified by our information-theoretical-based analyses. Empirically, our thorough experimental results show that CoCoNet outperforms the state-of-the-art self-supervised methods by a significant margin, for instance, CoCoNet beats the best benchmark method by an average margin of 1.1% on ImageNet.

Unsupervised domain adaptation (UDA) requires source domain samples with clean ground truth labels during training. Accurately labeling a large number of source domain samples is time-consuming and laborious. An alternative is to utilize samples with noisy labels for training. However, training with noisy labels can greatly reduce the performance of UDA. In this paper, we address the problem that learning UDA models only with access to noisy labels and propose a novel method called robust local preserving and global aligning network (RLPGA). RLPGA improves the robustness of the label noise from two aspects. One is learning a classifier by a robust informative-theoretic-based loss function. The other is constructing two adjacency weight matrices and two negative weight matrices by the proposed local preserving module to preserve the local topology structures of input data. We conduct theoretical analysis on the robustness of the proposed RLPGA and prove that the robust informative-theoretic-based loss and the local preserving module are beneficial to reduce the empirical risk of the target domain. A series of empirical studies show the effectiveness of our proposed RLPGA.

Although vision Transformers have achieved excellent performance as backbone models in many vision tasks, most of them intend to capture global relations of all tokens in an image or a window, which disrupts the inherent spatial and local correlations between patches in 2D structure. In this paper, we introduce a simple vision Transformer named SimViT, to incorporate spatial structure and local information into the vision Transformers. Specifically, we introduce Multi-head Central Self-Attention(MCSA) instead of conventional Multi-head Self-Attention to capture highly local relations. The introduction of sliding windows facilitates the capture of spatial structure. Meanwhile, SimViT extracts multiscale hierarchical features from different layers for dense prediction tasks. Extensive experiments show the SimViT is effective and efficient as a general-purpose backbone model for various image processing tasks. Especially, our SimViT-Micro only needs 3.3M parameters to achieve 71.1% top-1 accuracy on ImageNet-1k dataset, which is the smallest size vision Transformer model by now.

What matters for contrastive learning? We argue that contrastive learning heavily relies on informative features, or “hard” (positive or negative) features. Early works include more informative features by applying complex data augmentations and large batch size or memory bank, and recent works design elaborate sampling approaches to explore informative features. The key challenge toward exploring such features is that the source multi-view data is generated by applying random data augmentations, making it infeasible to always add useful information in the augmented data. Consequently, the informativeness of features learned from such augmented data is limited. In response, we propose to directly augment the features in latent space, thereby learning discriminative representations without a large amount of input data. We perform a meta learning technique to build the augmentation generator that updates its network parameters by considering the performance of the encoder. However, insufficient input data may lead the encoder to learn collapsed features and therefore malfunction the augmentation generator. A new margin-injected regularization is further added in the objective function to avoid the encoder learning a degenerate mapping. To contrast all features in one gradient back-propagation step, we adopt the proposed optimization-driven unified contrastive loss instead of the conventional contrastive loss. Empirically, our method achieves state-of-the-art results on several benchmark datasets.

Contrastive learning (CL)-based self-supervised learning models learn visual representations in a pairwise manner. Although the prevailing CL model has achieved great progress, in this paper, we uncover an ever-overlooked phenomenon: When the CL model is trained with full images, the performance tested in full images is better than that in foreground areas; when the CL model is trained with foreground areas, the performance tested in full images is worse than that in foreground areas. This observation reveals that backgrounds in images may interfere with the model learning semantic information and their influence has not been fully eliminated. To tackle this issue, we build a Structural Causal Model (SCM) to model the background as a confounder. We propose a backdoor adjustment-based regularization method, namely Interventional Contrastive Learning with Meta Semantic Regularizer (ICL-MSR), to perform causal intervention towards the proposed SCM. ICL-MSR can be incorporated into any existing CL methods to alleviate background distractions from representation learning. Theoretically, we prove that ICL-MSR achieves a tighter error bound. Empirically, our experiments on multiple benchmark datasets demonstrate that ICL-MSR is able to improve the performances of different state-of-the-art CL methods.

Recent works explore learning graph representations in a self-supervised manner. In graph contrastive learning, benchmark methods apply various graph augmentation approaches. However, most of the augmentation methods are non-learnable, which causes the issue of generating unbeneficial augmented graphs. Such augmentation may degenerate the representation ability of graph contrastive learning methods. Therefore, we motivate our method to generate augmented graph with a learnable graph augmenter, called MEta Graph Augmentation (MEGA). We then clarify that a "good" graph augmentation must have uniformity at the instance-level and informativeness at the feature-level. To this end, we propose a novel approach to learning a graph augmenter that can generate an augmentation with uniformity and informativeness. The objective of the graph augmenter is to promote our feature extraction network to learn a more discriminative feature representation, which motivates us to propose a meta-learning paradigm. Empirically, the experiments across multiple benchmark datasets demonstrate that MEGA outperforms the state-of-the-art methods in graph self-supervised learning tasks. Further experimental studies prove the effectiveness of different terms of MEGA. Our codes are available at https://github.com/hang53/MEGA.

As a successful approach to self-supervised learning, contrastive learning aims to learn invariant information shared among distortions of the input sample. While contrastive learning has yielded continuous advancements in sampling strategy and architecture design, it still remains two persistent defects: the interference of task-irrelevant information and sample inefficiency, which are related to the recurring existence of trivial constant solutions. From the perspective of dimensional analysis, we find out that the dimensional redundancy and dimensional confounder are the intrinsic issues behind the phenomena, and provide experimental evidence to support our viewpoint. We further propose a simple yet effective approach MetaMask, short for the dimensional Mask learned by Meta-learning, to learn representations against dimensional redundancy and confounder. MetaMask adopts the redundancy-reduction technique to tackle the dimensional redundancy issue and innovatively introduces a dimensional mask to reduce the gradient effects of specific dimensions containing the confounder, which is trained by employing a meta-learning paradigm with the objective of improving the performance of masked representations on a typical self-supervised task. We provide solid theoretical analyses to prove MetaMask can obtain tighter risk bounds for downstream classification compared to typical contrastive methods. Empirically, our method achieves state-of-the-art performance on various benchmarks.

Recently, significant progress has been made in masked image modeling to catch up to masked language modeling. However, unlike words in NLP, the lack of semantic decomposition of images still makes masked autoencoding (MAE) different between vision and language. In this paper, we explore a potential visual analogue of words, i.e., semantic parts, and we integrate semantic information into the training process of MAE by proposing a Semantic-Guided Masking strategy. Compared to widely adopted random masking, our masking strategy can gradually guide the network to learn various information, i.e., from intra-part patterns to inter-part relations. In particular, we achieve this in two steps. 1) Semantic part learning: we design a self-supervised part learning method to obtain semantic parts by leveraging and refining the multi-head attention of a ViT-based encoder. 2) Semantic-guided MAE (SemMAE) training: we design a masking strategy that varies from masking a portion of patches in each part to masking a portion of (whole) parts in an image. Extensive experiments on various vision tasks show that SemMAE can learn better image representation by integrating semantic information. In particular, SemMAE achieves 84.5% fine-tuning accuracy on ImageNet-1k, which outperforms the vanilla MAE by 1.4%. In the semantic segmentation and fine-grained recognition tasks, SemMAE also brings significant improvements and yields the state-of-the-art performance.

Video chat becomes more and more popular in our daily life. However, how to provide a high-quality video chat with the limited bandwidth is a key challenging task. In this paper, beyond the state-of-the-art video compression system, we propose an encoder-decoder joint enhancement algorithm for the video chat. In particular, the sparse map of the original frame is extracted at the encoder side and signaled to the decoder, which is utilized together with the sparse map of the decoded frame to obtain the boundary transformation map. In this manner, the boundary transformation map represents the key difference between the original frame and the decoded frame and hence can be used to enhance the decoded frame. Experimental results show that the proposed algorithm brings clear subjective and objective quality improvements. At the same quality, the proposed algorithm can achieve 35% bitrate savings compared to the VVC.

Deep learning has become increasingly popular for sequence modeling in various domains. In this work, we address the musical order verification as a sequential pattern learning task. We present a more advanced self-supervised learning model, dubbed as the triple-wise similarity with recurrent neural networks (TSN-R) which is on the basis of state-of-the-art Similarity Embedding Network. We take triple-wise musical sections as the input instance, and leverage the temporal coherence as a supervisory signal. As a first step, we use the triplet Siamese network as the input layer, and assess the similarity of the triplet feature maps. After that, we choose the bidirectional LSTM to extract features along the time dimension. Finally, the subsequent fully-connected layers are used for order verification. The experiments show that our approach outperforms other competing models in terms of prediction accuracy. Additionally, this paper reveals the reasons for the good performance of our model through the 2d-visualization of features. All the source code, pre-trained models and the experiment results are available in our project page. https://github.com/ISCASTEAM/Sequencing-the-musical-sections.

With the increasing demand for space service transmission, the satellite network is showing great commercial value. It is significant for LEO satellite network with tens of thousands of satellites to manage and schedule these resources. In this manuscript, a software defined satellite network (SDSN) architecture named OpenSatNet is designed on the basis of decoupling the data forwarding plane and the control plane in SDN network. Further, we formulate a multi-objective optimization problem considering time intervals, bandwidth, and the hops of each path, which is sloved by the proposed optimized forward scheduling algorithm (OFSA). The experiments are carried by comparing the existed SDRA and DRA with OFSA in terms of the scheduled tasks, success rate of scheduled tasks and transmission delay. The results show the effectiveness of the proposed OFSA.

Abstract Rendering with full lens model can offer images with photorealistic lens effects, but it leads to high computational costs. This paper proposes a novel camera lens model, NeuroLens, to emulate the imaging of real camera lenses through a data‐driven approach. The mapping of image formation in a camera lens is formulated as imaging regression functions (IRFs), which map input rays to output rays. IRFs are approximated with neural networks, which compactly represent the imaging properties and support parallel evaluation on a graphics processing unit (GPU). To effectively represent spatially varying imaging properties of a camera lens, the input space spanned by incident rays is subdivided into multiple subspaces and each subspace is fitted with a separate IRF. To further raise the evaluation accuracy, a set of neural networks is trained for each IRF and the output is calculated as the average output of the set. The effectiveness of the NeuroLens is demonstrated by fitting a wide range of real camera lenses. Experimental results show that it provides higher imaging accuracy in comparison to state‐of‐the‐art camera lens models, while maintaining the high efficiency for processing camera rays.

It is difficult to get accurate phase functions of water drops for simulating rainbows in ray tracers. Sadeghi's model calculates the phase functions of drops based on geometric optics and does some extra work to match the prediction of Lorenz-Mie theory, which is the most accurate solution currently to predict phase function of small spherical particles. The model is applied to ellipsoidal drops, which are difficult for Lorenz-Mie theory. Inspired by this model, an advanced physical optical model for simulating rainbows is implemented on PBRT in this paper. In the original model, when the phase function of a water drop is simulated with insufficient rays, the performance near the rainbow angles is poor. Our proposed model improves it by replacing bilinear interpolation with triangle interpolation and improving the intensity algorithm, which are more accurate near the rainbow angles and more efficient. Even with relatively insufficient rays, the accuracies near the rainbow angles in our model are still acceptable to a certain extent. The experimental results demonstrate that our model outperforms the original model.

Although the physical transmission rate increases rapidly, the quality of service (QoS) support for real-time traffic remains a challenge. 802.11 EDCA can only provide service differentiation, but not ensure the QoS as expected because of the restrained real-time traffic capacity and the uncertainty of prioritized access. This paper proposes a distributed MAC protocol called the Prioritized Access based on Busy Tone (PABT), which utilizes the in-band busy tone reservation, preemptive scheduling and adaptive CW tuning simultaneously to resolve the problems. Simulation results demonstrate that the proposed protocol provides a remarkable improvement in terms of the real-time traffic capacity, throughput and packet loss rate.

Backoff algorithm is a key component of contention-based MAC layer protocol. Numbers of dynamic CW adjustment methods have been proposed for the optimal throughput and fairness. However, they only utilize half-feedback information and may suffer from CW diverging problem. In this paper, we propose a novel Full-feedback Contention Window Adjustment (FCWA) backoff algorithm. Simulation results demonstrated that FCWA algorithm provides a remarkable performance improvement in terms of the short-term fairness, packet delay and delay jitter, while maintaining an optimal throughput close to the theoretical limit of the IEEE 802.11 access scheme.

A novel wave model is presented in this paper for realistically rendering diffraction and interference effects in ray-based renderers. The model indirectly simulate multibounce interference effects by means of the Wigner distribution function, where the bidirectional reflectance distribution function is constructed to encapsulate the phase variations. The approach is extended to directly compute phase variations in outgoing rays to render diffraction effects using the diffraction grating equation. We also implement an acceleration algorithm based on the current graphic hardware to gain realtime performance of rendering. The proposed model can be easily loaded into any ray-based renderer, and be used for rendering wave effects from surfaces with size of the wavelength.

This paper shows an optimizing stream-level authentication approach for secure and robust multimedia delivery over wireless networks. The proposed approach can achieve the optimum end-to-end authentic quality with a lower overhead. The received packet of codestreams is really effective to decrease the distortion, when it is both decodable and verifiable. Therefore, according to the coding and verification dependencies, an authentication optimization model (AOM) is designed to minimize the distortion and overhead. An implementation on the JPEG2000 codestream is realized via using the proposed AOM. By utilizing forward error correction (FEC) codes and hash chains, our approach can ensure that the verification dependencies are consistent with the coding dependencies. In other words, the proposed scheme does not cause quality degradations and it also reduce overhead redundancy. Experimental results demonstrate that our scheme achieves more optimizing end-to-end rate-distortion (R-D) performances at any packet-loss rate.

In this paper, an accurate and practical camera lens model is proposed to be applied in realistic rendering of lens-related effects. The optical modeling of this new model is firstly presented from two aspects: lens surface modeling and formulation of ray tracing equations. Then, a number of tunable models for controlling lens properties are introduced and combined together to determine overall imaging performance. An implementation framework for this lens model is presented from two important aspects: its internal working framework and a new rendering pipeline for integrating it into a general ray tracer. In contrast to existing lens models, this new one is characterized by its ability to accurately model the image formation process and its friendly tunable models to control its lens properties. As a consequence, it is capable of simulating complex lens-related effects without too much expertise on lens optics. Finally, multiple rendering experiments are performed to demonstrate the ability and usage of this novel model to simulate a variety of complex lens-related effects.

In this paper, the minimal visual coverage shortest path in raster terrain is studied with the proposal of a hypervolume contribution based multiobjective evolutionary approach. The main feature of the presented method is that all individuals in the population are periodically replaced by the selected non-dominated candidates in the archive based on hypervolume contribution, besides the well designed evolutionary operators and some popular techniques such as dominated relation and archive. Our algorithm may obtain well distributed Pareto set approximation efficiently, which is superior to the implementations based on the framework of NSGA-II and SMS EMOA with respect to the hypervolume.

Realistic rendering of large scale terrain scene in real-time is an important subject in virtual reality (VR) to construct a virtual environment with immersion and interactivity [Zhao 2009]. Large scale terrain scene visualization is popular in a variety of fields such as geographic information systems (GIS), military maneuvers, games, flight training and so on. Many visualization algorithms for terrain scenes have been proposed during the past decades, but to the authors' knowledge, approaches with high visual accuracy as well as low memory and time complexity have not been developed yet.

In this paper, trajectory planning for spacecraft formation reconfiguration is modeled as a MOP (multi-objective optimisation problem) and a niched evolutionary algorithm is proposed. With a problem specific real-valued representation of candidate solutions and evolutionary operators, the algorithm could find the time-fuel front of this problem and generate multiple solutions simultaneously. Higher selected probability of better individuals and the diversity of the front are guaranteed by equivalence class sharing. The algorithm is immune to issues of local minima and solutions are global optimal or near global optimal.

Based on evolutionary computation, a novel real-time route planner for unmanned air vehicles is presented. In the evolutionary route planner, the individual candidates are evaluated with respect to the workspace so that the computation of the configuration space is not required. The planner incorporates domain-specific knowledge, can handle unforeseeable changes of the environment, and take into account different kinds of mission constraints such as minimum route leg length and flying altitude, maximum turning angle, and fixed approach vector to goal position. Furthermore, the novel planner can be used to plan routes both for a single vehicle and for multiple ones. With Digital Terrain Elevation Data, the resultant routes can increase the surviving probability of the vehicles using the terrain masking effect.

Based on evolutionary computation, a new 3D route planner for unmanned air vehicles is presented. In our evolutionary route planner, the individual candidates are evaluated with respect to the workspace. Therefore a computation of the configuration space is avoided. With Digital Terrain Elevation Data, our approach can find a near-optimal route that can increase the surviving probability efficiently. By using a problem-specific representation of candidate solutions and genetic operators, the routes are generated in real-time and are able to take into account different kinds of mission constraints such as minimum route leg length and flying altitude, maximum turning angle, and fixed approach vector to goal position, etc.