Transformer has recently gained significant attention and achieved state-of-the-art performance in various computer vision applications, including image classification, instance segmentation, and object detection. However, the self-attention mechanism underlying the transformer leads to quadratic computational cost with respect to image size,limiting its widespread adoption in state-of-the-art vision backbones. In this paper we introduce an efficient and effective attention module we call Composite Attention. It features parallel branches, enabling the modeling of various global dependencies. In each composite attention module, one branch employs a dynamic channel attention module to capture global channel dependencies, while the other branch utilizes an efficient spatial attention module to extract long-range spatial interactions. In addition, we effectively blending composite attention module with convolutions, and accordingly develop a simple hierarchical vision backbone, dubbed CoAtFormer, by simply repeating the basic building block over multiple stages. Extensive experiments show our CoAtFormer achieves state-of-the-art results on various different tasks. Without any pre-training and extra data, CoAtFormer-Tiny, CoAtFormer-Small, and CoAtFormer-Base achieve 84.4%, 85.3%, and 85.9% top-1 accuracy on ImageNet-1K with 24M, 37M, and 73M parameters, respectively. Furthermore, CoAtFormer also consistently outperform prior work in other vision tasks such as object detection, instance segmentation, and semantic segmentation. When further pretraining on the larger dataset ImageNet-22k, we achieve 88.7% Top-1 accuracy on ImageNet-1K
论文检索
输入标题、作者或关键词，从 1,048 篇学术成果中精准定位
Popular transformer-based detectors detect objects in a one-to-one manner, where both the bounding box and category of each object are predicted only by the single query, leading to the box-sensitive category predictions. Additionally, the initialization of positional queries solely based on the predicted confidence scores or learnable embeddings neglects the significant spatial interrelation between different queries. This oversight leads to an imbalanced spatial distribution of queries (SDQ). In this paper, we propose a new MLP-DINO model to address these issues. Firstly, we present a new Query-Independent Category Supervision (QICS) approach for modeling categories information, decoupling the sensitive bounding box prediction process to improve the detection performance. Additionally, to further improve the category predictions, we introduce a deep MLP model into transformer-based detection framework to capture the long-range and short-range information simultaneously. Thirdly, to balance the SDQ, we design a novel Graph-based Query Selection (GQS) method that distributes each query point in a discrete manner by graphing the spatial information of queries to cover a broader range of potential objects, significantly enhancing the hit-rate of queries. Experimental results on COCO indicate that our MLP-DINO achieves 54.6% AP with only 44M parame ters under 36-epoch setting, greatly outperforming the original DINO by +3.7% AP with fewer parameters and FLOPs. The source codes will be available at https://github.com/Med-Process/MLP-DINO.
By learning expressive representations, deep learning (DL) has revolutionized autonomous driving (AD). Despite significant advancements, the inherent opacity of DL models engenders public distrust, impeding their widespread adoption. For explainable autonomous driving, current studies primarily concentrate on extracting features from input scenes to predict driving actions and their corresponding explanations. However, these methods underutilize semantics and correlation information within actions and explanations (collectively called categories in this work), leading to suboptimal performance. To address this issue, we propose Semantic-Guided Dynamic Correlation Learning (SGDCL), a novel approach that effectively exploits semantic richness and dynamic interactions intrinsic to categories. SGDCL employs a semantic-guided learning module to obtain category-specific representations and a dynamic correlation learning module to adaptively capture intricate correlations among categories. Additionally, we introduce an innovative loss term to leverage fine-grained co-occurrence statistics of categories for refined regularization. We extensively evaluate SGDCL on two well-established benchmarks, demonstrating its superiority over seven state-of-the-art baselines and a large vision-language model. SGDCL significantly promotes explainable autonomous driving with up to 15.3% performance improvement and interpretable attention scores, bolstering public trust in AD.
Object recognition in open environments, e.g., video surveillance, poses significant challenges due to the inclusion of unknown and multi-granularity tasks (MGT). However, recent methods exhibit limitations as they struggle to capture subtle differences between different parts within an object and adaptively handle MGT. To address this limitation, this paper proposes a Class-semantic Guided Attention Shift (SegAS) method. SegAS transforms adaptive MGT into dynamic combinations of invariant discriminant representations across different levels to effectively enhance adaptability to multi-granularity downstream tasks. Specifically, SegAS incorporates a hardness-based Attention Part Filtering Strategy (ApFS) to dynamically decompose objects into complementary parts based on the object structure and relevance to the instance. Then, SegAS shifts attention to the optimal discriminant region of each part under the guidance of hierarchical class semantics. Finally, a diversity loss is employed to emphasize the importance and distinction of different partial features. Extensive experiments validate SegAS' effectiveness in multi-granularity recognition of three tasks.
We introduce a Cascaded Diffusion Model (Cas-DM) that improves a Denoising Diffusion Probabilistic Model (DDPM) by effectively incorporating additional metric functions in training. Metric functions such as the LPIPS loss have been proven highly effective in consistency models derived from the score matching. However, for the diffusion counterparts, the methodology and efficacy of adding extra metric functions remain unclear. One major challenge is the mismatch between the noise predicted by a DDPM at each step and the desired clean image that the metric function works well on. To address this problem, we propose Cas-DM, a network architecture that cascades two network modules to effectively apply metric functions to the diffusion model training. The first module, similar to a standard DDPM, learns to predict the added noise and is unaffected by the metric function. The second cascaded module learns to predict the clean image, thereby facilitating the metric function computation. Experiment results show that the proposed diffusion model backbone enables the effective use of the LPIPS loss, improving the image quality (FID, sFID) of diffusion models on various established benchmarks.
Graph Neural Network (GNN)-based fake news detectors apply various methods to construct graphs, aiming to learn distinctive news embeddings for classification. Since the construction details are unknown for attackers in a black-box scenario, it is unrealistic to conduct the classical adversarial attacks that require a specific adjacency matrix. In this paper, we propose the first general black-box adversarial attack framework, i.e., General Attack via Fake Social Interaction (GAFSI), against detectors based on different graph structures. Specifically, as sharing is an important social interaction for GNN-based fake news detectors to construct the graph, we simulate sharing behaviors to fool the detectors. Firstly, we propose a fraudster selection module to select engaged users leveraging local and global information. In addition, a post injection module guides the selected users to create shared relations by sending posts. The sharing records will be added to the social context, leading to a general attack against different detectors. Experimental results on empirical datasets demonstrate the effectiveness of GAFSI.
Deep learning models, despite their remarkable success in various tasks, have been shown to be vulnerable to adversarial perturbations. Although robust learning techniques that consider adversarial risks against worst-case perturbations can effectively increase a model's robustness, they may not always be the most suitable approach. This is due to the fact that in certain scenarios, perturbations are more likely to occur probabilistically rather than being intentionally crafted by attackers. To address this challenge, we propose a novel risk-averse robust learning method based on entropic value-at-risk, called PRASS (Probabilistical Risk-Averse Robust Learning with Stochastic Search). Our approach leverages principles of stochastic optimisation and considers perturbing distributions rather than solely worst-case adversaries. By applying adaptive stochastic search to parameterised distributions, we further enhance the scalability of PRASS to handle distributional robustness. Empirical experiments demonstrate that PRASS outperforms existing state-of-the-art baselines.
Self-supervised learning (SSL) is capable of learning remarkable representations from centrally available data. Recent works further implement federated learning with SSL to learn from rapidly growing decentralized unlabeled images (e.g., from cameras and phones), often resulting from privacy constraints. Extensive attention has been paid to designing new frameworks or methods that achieve better performance for the SSL-based FL. However, such an effort has not yet taken the security of SSL-based FL into consideration. We aim to explore backdoor attacks in the context of SSL-based FL via an in-depth empirical study. In this paper, we propose a novel backdoor attack BADFSS against SSL-based FL. First, BADFSS learns a backdoored encoder via supervised contrastive learning on poison datasets constructed based on local datasets. Then, BADFSS employs attention alignment to enhance the backdoor effect and maintain the consistency between backdoored and global encoders. Moreover, we perform empirical evaluations of the proposed backdoor attacks on four datasets and compared BADFSS with three existing backdoor attacks that are transferred into federated self-supervised learning. The experiments demonstrate that BADFSS outperforms baseline methods and is effective under various settings.
Explanatory Artificial Intelligence plays a vital role in machine learning, due to its widespread application in decision-making scenarios, e.g., credit lending. Counterfactual Explanation (CFE) is a new kind of explanatory method that involves asking “what if ”, i.e. what would have happened if model inputs slightly change. To answer the question, Counterfactual Explanation aims at finding a minimum perturbation in model inputs leading to a different model decision. Compared with model-agnostic approaches, model-specific CFE approaches designed only for specific type of models usually have better performance in finding optimal counterfactual perturbations, owing to access to the inner workings of models. To deal with this dilemma, this work first proposes CMAES-based Counterfactual Explanations (CMACE): an effective model-agnostic counterfactual generating approach based on Covariance Matrix Adaptation Evolution Strategy (CMA-ES) and a warm starting scheme that provides good initialization of the counterfactual's mean and covariance parameters for CMA-ES taking advantage of prior information of training samples. CMACE significantly outperforms another state-of-art (SOTA) model-agnostic approach (Bayesian Counterfactual Generator, BayCon) with various experimental settings. Extensive experiments also demonstrate that CMACE is superior to a SOTA model-specific approach (Flexible Optimizable Counterfactual Explanations for Tree Ensembles, FOCUS) that is designed for tree-based models using gradient-based optimization.
Attribution algorithms play an instrumental role in human interpretation of AI models. The methods measure the importance of the input features to the model output decision, which can be displayed as an attribution map for image classifiers. Perturbation tests are the state-of-the-art approach to evaluate the quality of an attribution map. Unfortunately, we observe that perturbation tests fail to consider attribution magnitude, which translates into inconsistent quality scores. In this paper, we propose Magnitude Aligned Scoring (MAS), a new attribution quality metric that measures the alignment between the magnitude of the attributions and the model response. In particular, the metric accounts for both the relative ordering and the magnitude of the pixels within an attribution. In the experimental evaluation, we compare the MAS metric with existing metrics across a wide range of models, datasets, attributions, and evaluations. The results demonstrate that the MAS metric is 4x more sensitive to attribution changes, 2x more consistent, and 1.6x more invariant to baseline modifications. Our code and the referenced appendix are publicly available via https://github.com/chasewalker26/Magnitude-Aligned-Scoring.
Fairness and robustness are two important notions of learning models. Fairness ensures that models do not disproportionately harm (or benefit) some groups over others, while robustness measures the models' resilience against small input perturbations. While equally important properties, this paper illustrates a dichotomy between fairness and robustness, and analyzes when striving for fairness decreases the model robustness to adversarial samples. The reported analysis sheds light on the factors causing such contrasting behavior, suggesting that distance to the decision boundary across groups as a key factor. Experiments on non-linear models and different architectures validate the theoretical findings. In addition to the theoretical analysis, the paper also proposes a simple, yet effective, solution to construct models achieving good tradeoffs between fairness and robustness.
When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attacks
PDF ↗While in-processing fairness approaches show promise in mitigating bias predictions, their potential impact on privacy leakage remains under-explored. We aim to address this gap by assessing the privacy risks of fairness-enhanced binary classifiers with membership inference attacks (MIAs). Surprisingly, our results reveal that these fairness interventions exhibit increased resilience against existing attacks, indicating that enhancing fairness does not necessarily lead to privacy compromises. However, we find current attack methods are ineffective as they typically degrade into simple threshold models with limited attack effectiveness. Following this observation, we discover a novel threat dubbed Fairness Discrepancy Membership Inference Attacks (FD-MIA) that exploits prediction discrepancies between fair and biased models. This attack reveals more potent vulnerabilities and poses significant privacy risks to model privacy. Extensive experiments across multiple datasets, attack methods, and representative fairness approaches confirm our findings and demonstrate the efficacy of the proposed attack method. Our study exposes the overlooked privacy threats in fairness studies, advocating for thorough evaluations of potential security vulnerabilities before model deployments.
With the wide proliferation of Deep Neural Networks in high-stake applications, there is a growing demand for explainability behind their decision-making process. Concept learning models attempt to learn high-level 'concepts' - abstract entities that align with human understanding, and thus provide interpretability to DNN architectures. However, in this paper, we demonstrate that present SOTA concept learning approaches suffer from two major problems - lack of concept fidelity wherein the models fail to learn consistent concepts among similar classes and limited concept interoperability wherein the models fail to generalize learned concepts to new domains for the same task. Keeping these in mind, we propose a novel self-explaining architecture for concept learning across domains which - i) incorporates a new concept saliency network for representative concept selection, ii) utilizes contrastive learning to capture representative domain invariant concepts, and iii) uses a novel prototype-based concept grounding regularization to improve concept alignment across domains. We demonstrate the efficacy of our proposed approach over current SOTA concept learning approaches on four widely used real-world datasets. Empirical results show that our method improves both concept fidelity measured through concept overlap and concept interoperability measured through domain adaptation performance. An appendix of the paper with more comprehensive results can also be viewed at https://arxiv.org/abs/2405.00349.
Ten Words Only Still Help: Improving Black-Box AI-Generated Text Detection via Proxy-Guided Efficient Re-Sampling
PDF ↗With the rapidly increasing application of large language models (LLMs), their abuse has caused many undesirable societal problems such as fake news, academic dishonesty, and information pollution. This makes AI-generated text (AIGT) detection of great importance. Among existing methods, white-box methods are generally superior to black-box methods in terms of performance and generalizability, but they require access to LLMs' internal states and are not applicable to black-box settings. In this paper, we propose to estimate word generation probabilities as pseudo white-box features via multiple re-sampling to help improve AIGT detection under the black-box setting. Specifically, we design POGER, a proxy-guided efficient re-sampling method, which selects a small subset of representative words (e.g., 10 words) for performing multiple re-sampling in black-box AIGT detection. Experiments on datasets containing texts from humans and seven LLMs show that POGER outperforms all baselines in macro F1 under black-box, partial white-box, and out-of-distribution settings and maintains lower re-sampling costs than its existing counterparts.
By Fair Means or Foul: Quantifying Collusion in a Market Simulation with Deep Reinforcement Learning
PDF ↗In the rapidly evolving landscape of eCommerce, Artificial Intelligence (AI) based pricing algorithms, particularly those utilizing Reinforcement Learning (RL), are becoming increasingly prevalent. This rise has led to an inextricable pricing situation with the potential for market collusion. Our research employs an experimental oligopoly model of repeated price competition, systematically varying the environment to cover scenarios from basic economic theory to subjective consumer demand preferences. We also introduce a novel demand framework that enables the implementation of various demand models, allowing for a weighted blending of different models. In contrast to existing research in this domain, we aim to investigate the strategies and emerging pricing patterns developed by the agents, which may lead to a collusive outcome. Furthermore, we investigate a scenario where agents cannot observe their competitors’ prices. Finally, we provide a comprehensive legal analysis across all scenarios. Our findings indicate that RL-based AI agents converge to a collusive state characterized by the charging of supracompetitive prices, without necessarily requiring inter-agent communication. Implementing alternative RL algorithms, altering the number of agents or simulation settings, and restricting the scope of the agents’ observation space does not significantly impact the collusive market outcome behavior.
The ability to learn another’s moral beliefs is necessary for all social agents. It allows us to predict their behavior and is a prerequisite to correcting their beliefs if they are incorrect. To make AI systems more socially competent, a formal theory for learning internal normative beliefs is thus needed. However, to the best of our knowledge, a philosophically justified formal theory for this process does not yet exist. This paper begins the development of such a theory, focusing on learning from testimony. We make four main contributions. First, we provide a set of axioms that any such theory must satisfy. Second, we provide justification for belief functions, as opposed to traditional probability theory, for modeling norm learning. Third, we construct a novel learning function that satisfies these axioms. Fourth, we provide a complexity analysis of this formalism and proof that deontic rules are sound under its semantics. This paper thus serves as a theoretical contribution towards modeling learning norms from testimony, paving the road towards more social AI systems.
In this paper, we demonstrate the feasibility of alterfactual explanations for black box image classifiers. Traditional explanation mechanisms from the field of Counterfactual Thinking are a widely-used paradigm for Explainable Artificial Intelligence (XAI), as they follow a natural way of reasoning that humans are familiar with. However, most common approaches from this field are based on communicating information about features or characteristics that are especially important for an AI's decision. However, to fully understand a decision, not only knowledge about relevant features is needed, but the awareness of irrelevant information also highly contributes to the creation of a user's mental model of an AI system. To this end, a novel approach for explaining AI systems called alterfactual explanations was recently proposed on a conceptual level. It is based on showing an alternative reality where irrelevant features of an AI's input are altered. By doing so, the user directly sees which input data characteristics can change arbitrarily without influencing the AI's decision. In this paper, we show for the first time that it is possible to apply this idea to black box models based on neural networks. To this end, we present a GAN-based approach to generate these alterfactual explanations for binary image classifiers. Further, we present a user study that gives interesting insights on how alterfactual explanations can complement counterfactual explanations.
Federated Learning (FL) is a technique that allows multiple parties to train a shared model collaboratively without disclosing their private data. It has become increasingly popular due to its distinct privacy advantages. However, FL models can suffer from biases against certain demographic groups (e.g., racial and gender groups) due to the heterogeneity of data and party selection. Researchers have proposed various strategies for characterizing the group fairness of FL algorithms to address this issue. However, the effectiveness of these strategies in the face of deliberate adversarial attacks has not been fully explored. Although existing studies have revealed various threats (e.g., model poisoning attacks) against FL systems caused by malicious participants, their primary aim is to decrease model accuracy, while the potential of leveraging poisonous model updates to exacerbate model unfairness remains unexplored. In this paper, we propose a new type of model poisoning attack, EAB-FL, with a focus on exacerbating group unfairness while maintaining a good level of model utility. Extensive experiments on three datasets demonstrate the effectiveness and efficiency of our attack, even with state-of-the-art fairness optimization algorithms and secure aggregation rules employed. We hope this work will help the community fully understand the attack surfaces of current FL systems and facilitate corresponding mitigation to improve their resilience.
The design of Graph Transformers (GTs) often neglects considerations for fairness, resulting in biased outcomes against certain sensitive subgroups. Since GTs encode graph information without relying on message-passing mechanisms, conventional fairness-aware graph learning methods are not directly applicable to address these issues. To tackle this challenge, we propose FairGT, a Fairness-aware Graph Transformer explicitly crafted to mitigate fairness concerns inherent in GTs. FairGT incorporates a meticulous structural feature selection strategy and a multi-hop node feature integration method, ensuring independence of sensitive features and bolstering fairness considerations. These fairness-aware graph information encodings seamlessly integrate into the Transformer framework for downstream tasks. We also prove that the proposed fair structural topology encoding with adjacency matrix eigenvector selection and multi-hop integration are theoretically effective. Empirical evaluations conducted across five real-world datasets demonstrate FairGT's superiority in fairness metrics over existing graph transformers, graph neural networks, and state-of-the-art fairness-aware graph learning approaches.
As artificial intelligence (AI) technologies continue to influence our daily lives, there has been a growing need to ensure that AI enabled decision making systems adhere to principles expected of human decision makers. This need has given rise to the area of Machine Ethics. We formalise several ethical principles from the philosophical literature in the situation calculus framework to verify the ethical permissibility of a plan. Moreover, we propose several important properties, including some of our own that are intuitively appealing, and a number derived from the social choice literature that would appear to be relevant in evaluating the various approaches. Finally we provide an assessment of how our various situation calculus models of Machine Ethics that we examine satisfy the important properties we have identified.