Camouflage Images Generation (CIG) is an emerging research area that focuses on synthesizing images in which objects are harmoniously blended and exhibit high visual consistency with their surroundings. Existing methods perform CIG by either fusing objects into specific backgrounds or outpainting the surroundings via foreground object-guided diffusion. However, they often fail to obtain natural results because they overlook the logical relationship between camouflaged objects and background environments. To address this issue, we propose CT-CIG, a Controllable Text-guided Camouflage Images Generation method that produces realistic and logically plausible camouflage images. Leveraging Large Visual Language Models (VLM), we design a Camouflage-Revealing Dialogue Mechanism (CRDM) to annotate existing camouflage datasets with high-quality text prompts. Subsequently, the constructed image-prompt pairs are utilized to finetune Stable Diffusion, incorporating a lightweight controller to guide the location and shape of camouflaged objects for enhanced camouflage scene fitness. Moreover, we design a Frequency Interaction Refinement Module (FIRM) to capture high-frequency texture features, facilitating the learning of complex camouflage patterns. Extensive experiments, including CLIPScore evaluation and camouflage effectiveness assessment, demonstrate the semantic alignment of our generated text prompts and CT-CIG's ability to produce photorealistic camouflage images.

Domain Adaptive Person Search (DAPS) aims to improve the generalization capability of person search models by training on both labeled source data and unlabeled target data, which is not that practical in real-world applications considering the storage/transmission costs and the privacy of source data. In this paper, we investigate a more practical and efficient person search setting, Source-Free Domain Adaptive Person Search (SFDA-PS), which seeks to generalize an existing source person search model to any unseen domain without requiring source data. Considering the absence of effective annotations in SFDA-PS, we propose a Doubly Contrastive Learning (DCL) method to adapt the target domain knowledge to the source model in a mutual learning and contrastive learning way. Specifically, we employ a mutual learning-based mean-teacher model as our baseline to incorporate target domain knowledge by pursuing prediction consistency between the teacher and student. Then, a Relation-embedded Contrastive (ReC) learning strategy is introduced to the detection head to ensure semantic consistency among proposals related to the same person while maintaining semantic distinction among proposals from different categories or persons. Furthermore, a Memory-aided Constrative (MaC) learning strategy is integrated into the re-identification (Re-ID) head to enhance its discriminative capability on target person embeddings. Extensive experiments on existing state-of-the-art person search models and two widely used benchmarks demonstrate the superiority of the proposed SFDA-PS task, as well as our proposed DCL.

Camouflaged Object Detection (COD) presents a formidable challenge in computer vision due to the inherent difficulty of distinguishing the foreground from the background when objects are camouflaged. Inspired by research on optical imaging that proves the significance of depth of field for enhancing visual clarity and object separation, we introduce depth images into the COD framework to augment RGB data. In this paper, we propose a novel FocusNet that mimics the focusing process in photography. Specifically, we first propose a Dual-Modality Fusion (DMF) module to collaboratively learn deep features from both RGB and depth modalities, framing the whole concealed scene. Then, we propose another Depth Feature Focusing (DFF) module to fully exploit the localization cues in depth images, focusing on the foreground region. Finally, we propose the Hierarchical Feature Decoder (HFD) to generate accurate masks from multi-level features, capturing the camouflaged target. Extensive experiments demonstrate the effectiveness of the proposed FocusNet.

Camouflage images generation refers to concealing a salient object within a specific background by integrating its appearance with the surrounding environment. Previous approaches typically perform it by blending foreground and background images, which often suffer from 1) insufficient or excessive concealment, and 2) lack of effective evaluation metrics for assessing camouflage quality. To address these issues, we propose an Adaptive Camouflage Synthesizing network, named ACS-Net, which aims to generate images that effectively camouflage the object and minimize its salience. Specifically, a Multi-level Feature Aggregation Module (MFFM) is designed to improve the granularity of feature extraction, along with a Dual-branch Attention Enhancement Module (DAEM) for fore-back weight importance measurement to avoid excessive concealment. Subsequently, a Position-aligned Feature Fusion Module (PFFM) is utilized to effectively camouflage objects to an optimal extent guided by structural similarity. Furthermore, we employ detection methods for both camouflaged and salient objects to process our generated images as an unbiased evaluation for camouflage quality. Comprehensive experiments demonstrate that ACS-Net outperforms existing methods and is capable of generating high-quality camouflage images with an appropriate balance of concealment and salience. Code is available at https://github.com/NikoNairre/ACS-Net.

Person search is a challenging task in computer vision and multimedia understanding, which aims at localizing and identifying target individuals in realistic scenes. State-of-the-art models achieve remarkable success but suffer from overloaded computation and inefficient inference, making them impractical in most real-world applications. A promising approach to tackle this dilemma is to compress person search models with knowledge distillation (KD). Previous KD-based person search methods typically distill the knowledge from the re-identification (re-id) branch, completely overlooking the useful knowledge from the detection branch. In addition, we elucidate that the imbalance between person and background regions in feature maps has a negative impact on the distillation process. To this end, we propose a novel KD-based approach, namely Disaggregation Distillation for Person Search (DDPS), which disaggregates the distillation process and feature maps, respectively. Firstly, the distillation process is disaggregated into two task-oriented sub-processes,i.e., detection distillation and re-id distillation, to help the student learn both accurate localization capability and discriminative person embeddings. Secondly, we disaggregate each feature map into person and background regions, and distill these two regions independently to alleviate the imbalance problem. More concretely, three types of distillation modules,i.e., logit distillation (LD), correlation distillation (CD), and disaggregation feature distillation (DFD), are particularly designed to transfer comprehensive information from the teacher to the student. Note that such a simple yet effective distillation scheme can be readily applied to both homogeneous and heterogeneous teacher-student combinations. We conduct extensive experiments on two person search benchmarks, where the results demonstrate that, surprisingly, our DDPS enables the student model to surpass the performance of the corresponding teacher model, even achieving comparable results with general person search models.

Infrared (IR) images can be seen as complementary to visible light (RGB) images, as they can capture accurate targets in low-visibility conditions. However, camouflaged object detection (COD) based on RGB and IR images is expensive. To this end, we propose to exploit a style transfer-based data augmentation method to generate pseudo-IR images by absorbing the style information of IR images into RGB images, and to perform COD based on RGB and the pseudo-IR images. For RGB and IR-based COD, we propose a novel Edge-guided Uncertainty-aware Fusion Network (EUFNet), to make better use of the complementarity between the two kinds of images. Specifically, an uncertainty-aware fusion module is first proposed to aggregate RGB and IR features by estimating their uncertainties. Then, an edge enhancement module is proposed to extract and enhance the edge information in multiple stages. Lastly, a hierarchical integration module is designed to integrate RGB and IR features with edge cues. Extensive experiments demonstrate the effectiveness of the generated pseudo-IR images as well as the proposed EUFNet. The code is available at https://github.com/csdahunzi/COD.

As a classic semi-supervised approach, the Transductive Support Vector Machine (TSVM) has exhibited remarkable accuracy by utilizing unlabeled data. However, the robustness of TSVM against adversarial attacks remains a subject of investigation, prompting concerns about its reliability in security-critical applications. To unveil the vulnerability of TSVM, we introduce a finite-attack model specifically tailored to its characteristics, effectively manipulating its outputs. Additionally, we present Adversarial Defense-based TSVM (AD-TSVM), the first dedicated defense scheme designed for TSVM. AD-TSVM incorporates adversarial information into the optimization process, enhancing robustness by rebuilding a customized loss function and decision margin to counteract attacks. Rigorous experiments conducted on benchmark datasets demonstrate the effectiveness of AD-TSVM in significantly improving both the accuracy and stability of TSVM when confronted with adversarial attacks. This pioneering research assesses the weaknesses of TSVM and, more importantly, offers valuable insights and solutions for developing secure and trustworthy TSVM systems in the face of emerging threats.

Since semi-supervised learning can use fewer labelled samples to train a better model, semi-supervised methods are becoming popular in data mining. As an important algorithm of semi-supervised support vector machines (S3VM), transductive support vector machine (TSVM) sometimes may get worse models trained on both labelled samples and unlabelled samples than those trained only on labelled samples. To solve this problem, in this paper, we propose a safe TSVM (STSVM) based on the infinitesimal annealing algorithm. In the training of TSVM, we adopt the infinitesimal annealing and path following technology to approximate the step size of simulated annealing to balance the contradiction between annealing step and calculation time. During the annealing process, we call CP-step to update TSVM model with pseudo-labelled samples. If the current sample is on the boundary of combinatorial optimisation problem, SJ-step is called and a safety condition is designed to determine whether the sample needs to change its label or not, so as to ensure the TSVM model trained after changing is better than the model got before. The experimental results show that our STSVM algorithm can improve the accuracy of TSVM with a shorter running time, and is safer than the existing safe algorithms.

k nearest neighbor (kNN) is a simple and widely used classifier; it can achieve comparable performance with more complex classifiers including decision tree and artificial neural network. Therefore, kNN has been listed as one of the top 10 algorithms in machine learning and data mining. On the other hand, in many classification problems, such as medical diagnosis and intrusion detection, the collected training sets are usually class imbalanced. In class imbalanced data, although positive examples are heavily outnumbered by negative ones, positive examples usually carry more meaningful information and are more important than negative examples. Similar to other classical classifiers, kNN is also proposed under the assumption that the training set has approximately balanced class distribution, leading to its unsatisfactory performance on imbalanced data. In addition, under a class imbalanced scenario, the global resampling strategies that are suitable to decision tree and artificial neural network often do not work well for kNN, which is a local information‐oriented classifier. To solve this problem, researchers have conducted many works for kNN over the past decade. This paper presents a comprehensive survey of these works according to their different perspectives and analyzes and compares their characteristics. At last, several future directions are pointed out.

Semi-Supervised Support Vector Machine (S3VM) is one of the most popular methods for semi-supervised learning. To avoid the trivial solution of classifying all the unlabeled examples to a same class, balancing constraint is often used with S3VM (denoted as BCS3VM). Recently, a novel incremental learning algorithm (IL-S3VM) based on the path following technique was proposed to significantly scale up S3VM. However, the dynamic relationship of balancing constraint with previous labeled and unlabeled samples impede their incremental method for handling BCS3VM. To fill this gap, in this paper, we propose a new incremental S3VM algorithm (IL-BCS3VM) based on IL-S3VM which can effectively handle the balancing constraint and directly update the solution of BCS3VM. Specifically, to handle the dynamic relationship of balancing constraint with previous labeled and unlabeled samples, we design two unique procedures which can respectively eliminate and add the balancing constraint into S3VM. More importantly, we provide the finite convergence analysis for our IL-BCS3VM algorithm. Experimental results on a variety of benchmark datasets not only confirm the finite convergence of IL-BCS3VM, but also show a huge reduction of computational time compared with existing batch and incremental learning algorithms, while retaining the similar generalization performance.

Fisher discriminant analysis (FDA) is a classic supervised dimensionality reduction method in statistical pattern recognition. FDA can maximize the scatter between different classes, while minimizing the scatter within each class. As it only utilizes the labeled data and ignores the unlabeled data in the analysis process of FDA, it cannot be used to solve the unsupervised learning problems. Its performance is also very poor in dealing with semi-supervised learning problems in some cases. Recently, several semi-supervised learning methods as an extension of FDA have proposed. Most of these methods solve the semi-supervised problem by using a tradeoff parameter that evaluates the ratio of the supervised and unsupervised methods. In this paper, we propose a general semi-supervised dimensionality learning idea for the partially labeled data, namely the reconstruction probability class of labeled and unlabeled data. Based on the probability class optimizes Fisher criterion function, we propose a novel Semi-Supervised Local Fisher Discriminant Analysis (S2LFDA) method. Experimental results on real-world datasets demonstrate its effectiveness compared to the existing similar correlation methods.

Internetware challenges distributed systems in aspects from operating platforms, programming models, to engineering approaches, etc. Cloud computing based on virtualization is now a popular paradigm which can meet the dynamic resource allocation requirements of Internetware. Software entities dispersed on distributed nodes over the Internet, now are evolving into self-contained, autonomous software services. These software entities which are often deployed on virtual machines (VMs), are coordinated dynamically to achieve flexible design objectives. To improve the utilization of infrastructure resource, VMs processing components of a software should be consolidated to fewer physical machines (PMs). However, as the increasing trends of communication-intensive softwares, data traffic among VMs should be considered as well. And for the sake of safety and QoS (Quality of Service), certain VMs (e.g. backup nodes) are mutually-exclusive which means some VMs require to be placed on different PMs. In this paper, we investigate the online software placement problem with the target to minimize the network traffic cost, while taking into account the mutually-exclusiveness of VMs. We provide a formal problem description and its NP-hardness analysis. The proposed algorithm places the VMs that have heavy traffic on the same PM, while isolating the mutually-exclusive VMs simultaneously, which can guarantee high effectiveness and reliability for softwares in Internetware, respectively. The simulations show our algorithm reduces the traffic cost by 29% compared against the existing approaches.

Ranking support vector machine (RSVM) learning is equivalent to solving a convex quadratic programming problem. Currently there exists some difficulties for exact online ranking learning. This paper presents an exact and effective method that can solve the online ranking learning problem and shows the feasibility and finite convergence of the algorithm from the perspective of theoretical analysis. Additionally, this paper extends this method for online learning to offline ranking learning and offers another algorithm for solving large-scale RSVM.