Search

Real-world face recognition systems are vulnerable to diverse face attacks, ranging from digitally manipulated artifacts to physically crafted spoofing attacks. Existing works primarily focus on using an image classification network to address one type of attack but disregarding another. However, face recognition systems in real-world scenarios always encounter diverse simultaneous attacks, rendering the aforementioned single-attack detecting solution ineffective. Besides, excessive reliance on a classifier might easily fail when encountering face attacks with unknown patterns, as the category-level difference learned by classification backbones cannot generalize well to new attacks. Considering that real data are captured from actual individuals, while attack samples are generated by various distinct techniques, our focus is on extracting compact representations of real faces. This approach allows us to identify the fundamental differences between genuine and attack images, enabling us to address both manipulated artifacts and spoofing attacks simultaneously. Concretely, we propose a dual space reconstruction learning framework that models the commonalities of genuine faces in both spatial and frequency domains. With the learned characteristics of real faces, the model is more likely to segregate diverse attack samples as outliers from genuine images. Besides, we introduce a dynamic filtering module that filters out the redundant information retained by the reconstruction and enhances the critical divergence between the real and the attack to achieve better classification features. Since the training samples only cover limited style variations, which hampers the generalization to unseen domains, we further design a consistency regularized training strategy that mimics distribution shifts during training and imposes specific constraints to encourage style-irrelevant features. Moreover, in view of the lack of accessible benchmarks for unified evaluation of the detection competence against both face forgery and spoofing attacks, we set up a new challenging benchmark, named UniAttack, to foster the exploration of effective solutions to face attack detection. Both qualitative and quantitative results from existing and proposed benchmarks unequivocally demonstrate the superiority of our methods over state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have been showed to be highly vulnerable to imperceptible adversarial perturbations. As a complementary type of adversary, patch attacks that introduce perceptible perturbations to the images have attracted the interest of researchers. Existing patch attacks rely on the architecture of the model or the probabilities of predictions and perform poorly in the decision-based setting, which can still construct a perturbation with the minimal information exposed – the top-1 predicted label. In this work, we first explore the decision-based patch attack. To enhance the attack efficiency, we model the patches using paired key-points and use targeted images as the initialization of patches, and parameter optimizations are all performed on the integer domain. Then, we propose a differential evolutionary algorithm named DevoPatch for query-efficient decision-based patch attacks. Experiments demonstrate that DevoPatch outperforms the state-of-the-art black-box patch attacks in terms of patch area and attack success rate within a given query budget on image classification and face verification. Additionally, we conduct the vulnerability evaluation of ViT and MLP on image classification in the decision-based patch attack setting for the first time. Using DevoPatch, we can evaluate the robustness of models to black-box patch attacks. We believe this method could inspire the design and deployment of robust vision models based on various DNN architectures in the future. [ABSTRACT FROM AUTHOR]

Although great progress has been made in new electrolytes for lithium metal batteries (LMBs), the intrinsic relationship between electrolyte composition and cell performance remains unclear due to the lack of valid quantization method. Here, we proposed the concept of negative center of electrostatic potential (NCESP) and Mayer bond order (MBO) to describe solvent capability, which highly relate to solvation structure and oxidation potential, respectively. Based on established principles, the selected electrolyte with 1.7 M LiFSI in methoxytrimethylsilane (MOTMS)/ (trifluoromethyl)trimethylsilane (TFMTMS) shows unique hyperconjugation nature to stabilize both Li anode and high‐voltage cathode. The 4.6 V 30 μm Li||4.5 mAh cm−2 lithium cobalt oxide (LCO) (low N/P ratio of 1.3) cell with our electrolyte shows stable cycling with 91 % capacity retention over 200 cycles. The bottom‐up design concept of electrolyte opens up a general strategy for advancing high‐voltage LMBs. [ABSTRACT FROM AUTHOR]

Although great progress has been made in new electrolytes for lithium metal batteries (LMBs), the intrinsic relationship between electrolyte composition and cell performance remains unclear due to the lack of valid quantization method. Here, we proposed the concept of negative center of electrostatic potential (NCESP) and Mayer bond order (MBO) to describe solvent capability, which highly relate to solvation structure and oxidation potential, respectively. Based on established principles, the selected electrolyte with 1.7 M LiFSI in methoxytrimethylsilane (MOTMS)/ (trifluoromethyl)trimethylsilane (TFMTMS) shows unique hyperconjugation nature to stabilize both Li anode and high‐voltage cathode. The 4.6 V 30 μm Li||4.5 mAh cm−2 lithium cobalt oxide (LCO) (low N/P ratio of 1.3) cell with our electrolyte shows stable cycling with 91 % capacity retention over 200 cycles. The bottom‐up design concept of electrolyte opens up a general strategy for advancing high‐voltage LMBs. [ABSTRACT FROM AUTHOR]

Co-salient object detection (CoSOD) aims to detect common salient objects sharing the same attributes in an image group. The key issue of CoSOD is how to model the inter-saliency relations within an image group. The major limitation of previous methods is that they pre-define the group-to-one relations within an image group. In this paper, we propose a new concept of structural inter-saliency relations and solve the CoSOD with deep reinforcement learning framework. Firstly, we design a semantic relation graph (SRG) to model the structural inter-saliency relations. Then the feature selecting agent (FS-agent) aims to select the informative features, which can help the SRG effectively model structural inter-saliency relations. Finally, relation updating agent (RU-agent) progressively updates the SRG to focus on the co-salient relations like human decision-making process. Extensive experiments on co-saliency datasets show that because of well modeling inter-saliency relations in image group, our proposed method achieves superior performance compared to the state-of-the-art methods. We hope that this paper can motivate future research for visual co-analysis tasks. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel model for simultaneous stable co-saliency detection (CoSOD) and object co-segmentation (CoSEG). To detect co-saliency (segmentation) accurately, the core problem is to well model inter-image relations between an image group. Some methods design sophisticated modules, such as recurrent neural network (RNN), to address this problem. However, order-sensitive problem is the major drawback of RNN, which heavily affects the stability of proposed CoSOD (CoSEG) model. In this paper, inspired by RNN-based model, we first propose a multi-path stable recurrent unit (MSRU), containing dummy orders mechanisms (DOM) and recurrent unit (RU). Our proposed MSRU not only helps CoSOD (CoSEG) model captures robust inter-image relations, but also reduces order-sensitivity, resulting in a more stable inference and training process. Moreover, we design a cross-order contrastive loss (COCL) that can further address order-sensitive problem by pulling close the feature embedding generated from different input orders. We validate our model on five widely used CoSOD datasets (CoCA, CoSOD3k, Cosal2015, iCoseg and MSRC), and three widely used datasets (Internet, iCoseg and PASCAL-VOC) for object co-segmentation, the performance demonstrates the superiority of the proposed approach as compared to the state-of-the-art (SOTA) methods. [ABSTRACT FROM AUTHOR]

A high‐fidelity colour transfer should align the colour distributions between images and meanwhile avoid the damage to the original structure. However, the traditional methods often fail to yield high‐fidelity transfer results due to some existing tone and structure artefacts. In this study, the authors propose a new framework to effectively integrate the tone and structure refinements of colour transfer. They develop the ideas of image decomposition and gradient guidance to perform tone reconstruction while protecting original structure. Its overall flow includes the five key steps: tone clustering, structure extraction, structure optimisation, gradient‐guided tone reconstruction, and structure restoration. Moreover, they propose an evaluation metric to measure the differences of tone and structure between images. They demonstrate the performance of the proposed method through a number of experiments in visual comparison and objective evaluation. [ABSTRACT FROM AUTHOR]

Automatic decomposition of intrinsic images, especially for complex real-world images, is a challenging under-constrained problem. Thus, we propose a new algorithm that generates and combines multi-scale properties of chromaticity differences and intensity contrast. The key observation is that the estimation of image reflectance, which is neither a pixel-based nor a region-based property, can be improved by using multi-scale measurements of image content. The new algorithm iteratively coarsens a graph reflecting the reflectance similarity between neighbouring pixels. Then multi-scale reflectance properties are aggregated so that the graph reflects the reflectance property at different scales. This is followed by a L0 sparse regularization on the whole reflectance image, which enforces the variation in reflectance images to be high-frequency and sparse. We formulate this problem through energy minimization which can be solved efficiently within a few iterations. The effectiveness of the new algorithm is tested with the Massachusetts Institute of Technology (MIT) dataset, the Intrinsic Images in the Wild (IIW) dataset, and various natural images. [ABSTRACT FROM AUTHOR]

The objective of intrinsic images estimation is to decompose an input image into its intrinsic shading and reflectance components. This is a well-known under-constrained problem that has long been an open challenge. This paper proposes a novel approach for automatic intrinsic images decomposition that uses a new reflectance sparsity prior. On the basis of the observation that the reflectance of natural objects is commonly piecewise constant, we formalize this constraint on the entire reflectance image using the $$L_0$$ sparse loss function that enforces the variation in reflectance images to be of high-frequency and sparse. This new sparsity constraint significantly improves the quality of Retinex intrinsic images estimation. It also functions effectively by combining a class of global sparsity priors on reflectance. Experimental results on MIT benchmark dataset as well as various real-world images and synthetic images demonstrate the effectiveness and versatility of our approach. [ABSTRACT FROM AUTHOR]