相关论文: One-vs-the-Rest Loss to Focus on Important Samples…

Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples. This paper proposes an adaptive margin principle to improve…

Real-world classification problems typically exhibit an imbalanced or long-tailed label distribution, wherein many labels are associated with only a few samples. This poses a challenge for generalisation on such labels, and also makes…

Previous adversarial training raises model robustness under the compromise of accuracy on natural data. In this paper, we reduce natural accuracy degradation. We use the model logits from one clean model to guide learning of another one…

The cross entropy loss is widely used due to its effectiveness and solid theoretical grounding. However, as training progresses, the loss tends to focus on hard to classify samples, which may prevent the network from obtaining gains in…

Adversarial examples provide an opportunity as well as impose a challenge for understanding image classification systems. Based on the analysis of the adversarial training solution Adversarial Logits Pairing (ALP), we observed in this work…

This paper illustrates the central role of loss functions in data-driven decision making, providing a comprehensive survey on their influence in cost-sensitive classification (CSC) and reinforcement learning (RL). We demonstrate how…

Adversarial defenses train deep neural networks to be invariant to the input perturbations from adversarial attacks. Almost all defense strategies achieve this invariance through adversarial training i.e. training on inputs with adversarial…

Recent reasoning large language models (LLMs), such as OpenAI o1 and DeepSeek-R1, exhibit strong performance on complex tasks through test-time inference scaling. However, prior studies have shown that these models often incur significant…

Previous work shows that adversarially robust generalization requires larger sample complexity, and the same dataset, e.g., CIFAR-10, which enables good standard accuracy may not suffice to train robust models. Since collecting new training…

Understanding the fundamental limits of robust supervised learning has emerged as a problem of immense interest, from both practical and theoretical standpoints. In particular, it is critical to determine classifier-agnostic bounds on the…

Deep Neural Networks (DNNs) have shown substantial success in various applications but remain vulnerable to adversarial attacks. This study aims to identify and isolate the components of two different adversarial training techniques that…

Despite the undeniable progress in visual recognition tasks fueled by deep neural networks, there exists recent evidence showing that these models are poorly calibrated, resulting in over-confident predictions. The standard practices of…

Deep neural networks can be easily fooled into making incorrect predictions through corruption of the input by adversarial perturbations: human-imperceptible artificial noise. So far adversarial training has been the most successful defense…

Deep Neural Networks are susceptible to adversarial perturbations. Adversarial training and adversarial purification are among the most widely recognized defense strategies. Although these methods have different underlying logic, both rely…

Large annotated datasets inevitably contain noisy labels, which poses a major challenge for training deep neural networks as they easily memorize the labels. Noise-robust loss functions have emerged as a notable strategy to counteract this…

Conventional semi-supervised contrastive learning methods assign pseudo-labels only to samples whose highest predicted class probability exceeds a predefined threshold, and then perform supervised contrastive learning using those selected…

Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classes. We design two novel methods to improve performance in…

Deep neural networks (DNNs) are vulnerable to adversarial examples, in which DNNs are misled to false outputs due to inputs containing imperceptible perturbations. Adversarial training, a reliable and effective method of defense, may…

Fast adversarial training (FAT) is beneficial for improving the adversarial robustness of neural networks. However, previous FAT work has encountered a significant issue known as catastrophic overfitting when dealing with large perturbation…

We explore loss functions for fact verification in the FEVER shared task. While the cross-entropy loss is a standard objective for training verdict predictors, it fails to capture the heterogeneity among the FEVER verdict classes. In this…