Open-Vocabulary Multi-Label Image Classification (OV-MLIC) is an emerging task in computer vision aimed at recognizing unseen categories in real-world scenarios, leveraging Vision and Language Pre-training (VLP) models like CLIP. However, existing methods overlook the impact of category coupling and scale variation on cross-category knowledge transfer, thereby restricting performance on unseen categories. To address this issue, we propose a novel OV-MLIC method called Hierarchical Dual-Granularity Alignment-CLIP (HDG-CLIP), which emphasizes the complementary characteristics of different modalities and introduces a sample-category matching mechanism. Specifically, to address the category coupling issue, we construct semantic category prototypes to enhance cross-category knowledge transfer. Through the interaction between visual embeddings and category prototypes, we decouple category-specific information from mixed visual features and leverage the visual context of samples to learn category-level visual features. For mitigating the scale variation issue, we build a sample-category dual-granularity matching mechanism based on the difference in capture capability of different modalities across scales, thereby improving the object localization accuracy from a multi-dimensional perspective. Extensive experimental results show that HDG-CLIP exhibits state-of-art performance over existing methods on both the NUS-WIDE and the Open-Images datasets. Our code is available at https://github.com/wakihy/HDG-CLIP.

Multi-objective decision-making problems have emerged in numerous real-world scenarios, such as video games, navigation and robotics. Considering the clear advantages of Reinforcement Learning (RL) in optimizing decision-making processes, researchers have delved into the development of Multi-Objective RL (MORL) methods for solving multi-objective decision problems. However, previous methods either cannot obtain the entire Pareto front, or employ only a single policy network for all the preferences over multiple objectives, which may not produce personalized solutions for each preference. To address these limitations, we propose a novel decomposition-based framework for MORL, Pareto Set Learning for MORL (PSL-MORL), that harnesses the generation capability of hypernetwork to produce the parameters of the policy network for each decomposition weight, generating relatively distinct policies for various scalarized subproblems with high efficiency. PSL-MORL is a general framework, which is compatible for any RL algorithm. The theoretical result guarantees the superiority of the model capacity of PSL-MORL and the optimality of the obtained policy network. Through extensive experiments on diverse benchmarks, we demonstrate the effectiveness of PSL-MORL in achieving dense coverage of the Pareto front, significantly outperforming state-of-the-art MORL methods in both the hypervolume and sparsity indicators.

In multiobjective optimization, the R2 indicator is widely used for designing the indicator-based algorithms, and the Tchebycheff approach is commonly employed in the decomposition-based algorithms. Despite their wide use, the connection between these two different paradigms is still not well understood, particularly in the field of multiobjective efficient global optimization (MOEGO). Considering that expected improvement (EI) is a cornerstone in efficient global optimization (EGO), this article first studies the relationship between R2-based EI and Tchebycheff-based EI. Then, we introduce a many-to-few (M2F) decomposition framework, offering a new perspective for linking the R2-based method and the Tchebycheff decomposition approach. By incorporating M2F decomposition into MOEGO, a new algorithm called R2/D-EGO is proposed. At each iteration, R2/D-EGO utilizes the Tchebycheff decomposition paradigm to generate a set of candidate solutions, each one corresponding to a different weight vector. Subsequently, a subset of query points is selected from the candidates based on the lower bound of R2-based EI. Empirical results indicate that the proposed R2/D-EGO is highly competitive in comparison with both the R2-based and decomposition-based MOEGO algorithms in the parallel (or batch) setting.

Bayesian optimization (BO) is a sample-efficient method and has been widely used for optimizing expensive black-box functions. Recently, there has been a considerable interest in BO literature in optimizing functions that are affected by context variable in the environment, which is uncontrollable by decision makers. In this paper, we focus on the optimization of functions' expectations over continuous context variable, subject to an unknown distribution. To address this problem, we propose two algorithms that employ kernel density estimation to learn the probability density function (PDF) of continuous context variable online. The first algorithm is simpler, which directly optimizes the expectation under the estimated PDF. Considering that the estimated PDF may have high estimation error when the true distribution is complicated, we further propose the second algorithm that optimizes the distributionally robust objective. Theoretical results demonstrate that both algorithms have sub-linear Bayesian cumulative regret on the expectation objective. Furthermore, we conduct numerical experiments to empirically demonstrate the effectiveness of our algorithms.

Offline optimization aims to maximize a black-box objective function with a static dataset and has wide applications. In addition to the objective function being black-box and expensive to evaluate, numerous complex real-world problems entail optimizing multiple conflicting objectives, i.e., multi-objective optimization (MOO). Nevertheless, offline MOO has not progressed as much as offline single-objective optimization (SOO), mainly due to the lack of benchmarks like Design-Bench for SOO. To bridge this gap, we propose a first benchmark for offline MOO, covering a range of problems from synthetic to real-world tasks. This benchmark provides tasks, datasets, and open-source examples, which can serve as a foundation for method comparisons and advancements in offline MOO. Furthermore, we analyze how the current related methods can be adapted to offline MOO from four fundamental perspectives, including data, model architecture, learning algorithm, and search algorithm. Empirical results show improvements over the best value of the training set, demonstrating the effectiveness of offline MOO methods. As no particular method stands out significantly, there is still an open challenge in further enhancing the effectiveness of offline MOO. We finally discuss future challenges for offline MOO, with the hope of shedding some light on this emerging field. Our code is available at https://github.com/lamda-bbo/offline-moo.

Bayesian optimization (BO) is a popular method for computationally expensive black-box optimization. However, traditional BO methods need to solve new problems from scratch, leading to slow convergence. Recent studies try to extend BO to a transfer learning setup to speed up the optimization, where search space transfer is one of the most promising approaches and has shown impressive performance on many tasks. However, existing search space transfer methods either lack an adaptive mechanism or are not flexible enough, making it difficult to efficiently identify promising search space during the optimization process. In this paper, we propose a search space transfer learning method based on Monte Carlo tree search (MCTS), called MCTS-transfer, to iteratively divide, select, and optimize in a learned subspace. MCTS-transfer can not only provide a well-performing search space for warm-start but also adaptively identify and leverage the information of similar source tasks to reconstruct the search space during the optimization process. Experiments on synthetic functions, real-world problems, Design-Bench and hyper-parameter optimization show that MCTS-transfer can demonstrate superior performance compared to other search space transfer methods under different settings. Our code is available at \url{https://github.com/lamda-bbo/mcts-transfer}.

In order to reduce the probability of leakage and improve detection accuracy, multiple radar equipment is required to perform multiple detections on the same airspace. Due to the overlap of airspace, there are multiple local tracks reported by various radar equipment that belong to the same target. The local tracks reported by each radar require track fusion to form a system track, and track association is a prerequisite for track fusion. This paper proposes a multi-target and multi-sensor track association analysis method, which can distinguish whether local tracks come from the same target and associate local tracks with the same target, providing conditions for track fusion to form system tracks. This method divides track association into two steps: Coarse association and fine association, which greatly improves the accuracy of track association.

The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Thus, benchmarking and advancing techniques detecting digital manipulation become an urgent issue. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology, which does not involve the most recent technologies like diffusion. The diversity and quality of images generated by diffusion models have been significantly improved and thus a much more challenging face forgery dataset shall be used to evaluate SOTA forgery detection literature. In this paper, we propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection, which contains a large number of forgery faces generated by advanced generators such as the diffusion-based model and more detailed labels about the manipulation approaches and adopted generators. In addition to evaluating SOTA approaches on our benchmark, we design an innovative Cross Appearance-Edge Learning (CAEL) detector to capture multi-grained appearance and edge global representations, and detect discriminative and general forgery traces. Moreover, we devise an Appearance-Edge Cross-Attention (AECA) module to explore the various integrations across two domains. Extensive experiment results and visualizations show that our detection model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Code and datasets will be available athttps://github.com/Jenine-321/GenFace.

Face anti-spoofing (FAS) defends the facial image recognition systems against the spoof attacks. While the imperceptible spoof cues in the facial images are usually represented in the images' high-frequency components, existing methods do not fully explore them. In this paper, we introduce wavelet into face anti-spoofing and propose a Cross-frequency Dual-branch network (CDNet), which mainly contains two frequency branches to explore spoof cues from the input facial images' high- and low-frequency components generated by wavelet transforms. In CDNet, we design Frequency Attention Module (FAM) to fuse different internal frequency features learned by two frequency branches, and propose a Complementary Learning Module (CLM) to aggregate the two final frequency features. In addition, we present a resolution-aware Binary Cross-Entropy Loss to balance the training samples with different resolutions. We conduct comprehensive experiments on four datasets, and the results shows that our CDNet performs better than the previous state-of-the-art methods on both intra- and inter-dataset testing.

Bayesian optimization (BO) is a class of popular methods for expensive black-box optimization, and has been widely applied to many scenarios. However, BO suffers from the curse of dimensionality, and scaling it to high-dimensional problems is still a challenge. In this paper, we propose a variable selection method MCTS-VS based on Monte Carlo tree search (MCTS), to iteratively select and optimize a subset of variables. That is, MCTS-VS constructs a low-dimensional subspace via MCTS and optimizes in the subspace with any BO algorithm. We give a theoretical analysis of the general variable selection method to reveal how it can work. Experiments on high-dimensional synthetic functions and real-world problems (e.g., MuJoCo locomotion tasks) show that MCTS-VS equipped with a proper BO optimizer can achieve state-of-the-art performance.

In this letter, considering the simultaneous wireless information and power transfer scheme, we study the robust artificial noise (AN)-aided secure transmission design in multiple-input-single-output channels where the channel uncertainties are modeled by worst-case model. Our objective is to maximize the worst-case secrecy rate with respect to both the worst-case channel uncertainties and the worst-case eavesdropper among multiple eavesdroppers, under the transmit power constraint and the worst-case energy harvesting constraint. The optimal solution to the problem can be found by two-dimensional (2-D) search. Since the 2-D search algorithm has high computational complexity, we propose to neglect the correlation of the channel uncertainties from the transmitter to the information-decoding receiver and reformulate the problem as a sequence of convex semidefinite programming (SDP) which is solved efficiently by SDP based one-dimensional line search method. It is shown through computer simulations that the proposed robust AN-aided secure transmission schemes have significant performance gain over the non-robust AN-aided secure transmission scheme and the robust secure transmission scheme without the aid of AN.

Considering simultaneous wireless information and power transfer (SWIPT), we investigate cooperative-jamming (CJ) aided robust secure transmission design in multiple-input-single-output channels, where a cooperative jammer introduces jamming interferences and assists a source to supply wireless power for both an energy receiver and a legitimate destination. The destination employs a power splitting (PS) scheme to split the received signals for both information decoding and energy harvesting (EH). Compared with conventional transmission without SWIPT, the transmission with SWIPT should satisfy additional worst-case EH constraints. Furthermore, the PS scheme introduces an additional multiplicative optimization variable, i.e., the PS factor. Our objective is to maximize worst-case secrecy rate under transmit power constraints and worst-case EH constraints. We propose to decouple the problem into three optimization problems and employ alternating optimization algorithm to obtain the locally optimal solution. For the optimization of transmit covariance matrices and PS factor, we propose to employ the S-procedure and its extension to reformulate it as a convex semidefinite programming. It is shown through the simulation results that our proposed CJ aided robust secure transmission scheme outperforms the robust direct transmission scheme without CJ and the CJ aided non-robust scheme.