Related papers: SEDA: Self-Ensembling ViT with Defensive Distillat…

Vision-language models (VLMs) are vulnerable to adversarial image perturbations. Existing works based on adversarial training against task-specific adversarial examples are computationally expensive and often fail to generalize to unseen…

Colorectal liver metastases (CLM) significantly impact colon cancer patients, influencing survival based on systemic chemotherapy response. Traditional methods like tumor grading scores (e.g., tumor regression grade - TRG) for prognosis…

Due to the shortage of COVID-19 viral testing kits and the long waiting time, radiology imaging is used to complement the screening process and triage patients into different risk levels. Deep learning based methods have taken an active…

DEtection TRansformer (DETR) becomes a dominant paradigm, mainly due to its common architecture with high accuracy and no post-processing. However, DETR suffers from unstable training dynamics. It consumes more data and epochs to converge…

In the field of medical imaging, the advent of deep learning, especially the application of convolutional neural networks (CNNs) has revolutionized the analysis and interpretation of medical images. Nevertheless, deep learning methods…

Video object segmentation is a fundamental research problem in computer vision. Recent techniques have often applied attention mechanism to object representation learning from video sequences. However, due to temporal changes in the video…

Self-supervised learning has revolutionized medical imaging by enabling efficient and generalizable feature extraction from large-scale unlabeled datasets. Recently, self-supervised foundation models have been extended to three-dimensional…

Deploying high-performance dense prediction models on resource-constrained edge devices remains challenging due to strict limits on computation and memory. In practice, lightweight systems for object detection, instance segmentation, and…

Recent works in self-supervised learning have shown impressive results on single-object images, but they struggle to perform well on complex multi-object images as evidenced by their poor visual grounding. To demonstrate this concretely, we…

We propose a selective learning method using meta-learning and deep reinforcement learning for medical image interpretation in the setting of limited labeling resources. Our method, MedSelect, consists of a trainable deep learning selector…

Large pre-trained transformer-based language models have achieved impressive results on a wide range of NLP tasks. In the past few years, Knowledge Distillation(KD) has become a popular paradigm to compress a computationally expensive model…

Recently, an event-based end-to-end model (SEDT) has been proposed for sound event detection (SED) and achieves competitive performance. However, compared with the frame-based model, it requires more training data with temporal annotations…

Methods for improving deep neural network training times and model generalizability consist of various data augmentation, regularization, and optimization approaches, which tend to be sensitive to hyperparameter settings and make…

Despite providing high-performance solutions for computer vision tasks, the deep neural network (DNN) model has been proved to be extremely vulnerable to adversarial attacks. Current defense mainly focuses on the known attacks, but the…

Vision Transformers (ViTs) have achieved state-of-the-art performance for various vision tasks. One reason behind the success lies in their ability to provide plausible innate explanations for the behavior of neural architectures. However,…

Malware detection plays a crucial role in cyber-security with the increase in malware growth and advancements in cyber-attacks. Previously unseen malware which is not determined by security vendors are often used in these attacks and it is…

Deep neural networks are susceptible to human imperceptible adversarial perturbations. One of the strongest defense mechanisms is \emph{Adversarial Training} (AT). In this paper, we aim to address two predominant problems in AT. First,…

Adversarial attacks pose a significant threat to deep learning models, particularly in safety-critical applications like healthcare and autonomous driving. Recently, patch based attacks have demonstrated effectiveness in real-time inference…

Vision Transformers are increasingly embedded in industrial systems due to their superior performance, but their memory and power requirements make deploying them to edge devices a challenging task. Hence, model compression techniques are…

Vision Transformers (ViTs) have a radically different architecture with significantly less inductive bias than Convolutional Neural Networks. Along with the improvement in performance, security and robustness of ViTs are also of great…