相关论文: SEDA: Self-Ensembling ViT with Defensive Distillat…

We propose a conceptually simple and lightweight framework for improving the robustness of vision models through the combination of knowledge distillation and data augmentation. We address the conjecture that larger models do not make for…

Self-Supervised Learning (SSL) has become a prominent paradigm for pre-training encoders to learning general-purpose representations from unlabeled data and releasing them on third-party platforms for broad downstream deep learning tasks.…

In standard adversarial training, models are optimized to fit one-hot labels within allowable adversarial perturbation budgets. However, the ignorance of underlying distribution shifts brought by perturbations causes the problem of robust…

Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In previous studies, the use of models encrypted with a secret key was demonstrated to be robust against white-box attacks, but not against black-box…

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. The most recent UDA methods always resort to adversarial training to yield state-of-the-art results and a dominant…

In real application scenarios, it is often challenging to obtain a large amount of labeled data for speaker representation learning due to speaker privacy concerns. Self-supervised learning with no labels has become a more and more…

In this paper, we compare three privacy-preserving distributed learning techniques: federated learning, split learning, and SplitFed. We use these techniques to develop binary classification models for detecting tuberculosis from chest…

Tuberculosis (TB) remains a significant global health challenge, with pediatric cases posing a major concern. The World Health Organization (WHO) advocates for chest X-rays (CXRs) for TB screening. However, visual interpretation by…

In clinics, doctors rely on electrocardiograms (ECGs) to assess severe cardiac disorders. Owing to the development of technology and the increase in health awareness, ECG signals are currently obtained by using medical and commercial…

The successful application of large pre-trained models such as BERT in natural language processing has attracted more attention from researchers. Since the BERT typically acts as an end-to-end black box, classification systems based on it…

Deep neural networks often suffer performance degradation upon deployment due to distribution shifts. Continual Test-Time Adaptation (CTTA) aims to address this issue in an unsupervised manner. However, existing methods that rely on…

In this paper, we investigate the continual learning of Vision Transformers (ViT) for the challenging exemplar-free scenario, with special focus on how to efficiently distill the knowledge of its crucial self-attention mechanism (SAM). Our…

In this paper, we ask whether Vision Transformers (ViTs) can serve as an underlying architecture for improving the adversarial robustness of machine learning models against evasion attacks. While earlier works have focused on improving…

Following the success in advancing natural language processing and understanding, transformers are expected to bring revolutionary changes to computer vision. This work provides a comprehensive study on the robustness of vision transformers…

Standard Latent Diffusion Models rely on a complex, three-part architecture consisting of a separate encoder, decoder, and diffusion network, which are trained in multiple stages. This modular design is computationally inefficient, leads to…

Vision transformers (ViTs) have become essential backbones in advanced computer vision applications and multi-modal foundation models. Despite their strengths, ViTs remain vulnerable to adversarial perturbations, comparable to or even…

Adversarial attacks pose significant challenges for vision models in critical fields like healthcare, where reliability is essential. Although adversarial training has been well studied in natural images, its application to biomedical and…

Self-Supervised Learning (SSL) for Vision Transformers (ViTs) has recently demonstrated considerable potential as a pre-training strategy for a variety of computer vision tasks, including image classification and segmentation, both in…

Vision Transformers (ViTs) have achieved remarkable success in computer vision tasks. However, their potential in rotation-sensitive scenarios has not been fully explored, and this limitation may be inherently attributed to the lack of…

Deep learning is transforming microscopy, yet models often fail when applied to images from new instruments or acquisition settings. Conventional adversarial domain adaptation (ADDA) retrains entire networks, often disrupting learned…