Despite their success, deep networks have been shown to be highly susceptible to perturbations, often causing significant drops in accuracy. In this paper, we investigate model robustness on perturbed inputs by studying the performance of internal sub-networks (subnets). Interestingly, we observe that most subnets show particularly poor robustness against perturbations. More importantly, these weak subnets are correlated with the overall lack of robustness. Tackling this phenomenon, we propose a new training procedure that identifies and enhances weak subnets (EWS) to improve robustness. Specifically, we develop a search algorithm to find particularly weak subnets and explicitly strengthen them via knowledge distillation from the full network. We show that EWS greatly improves both robustness against corrupted images as well as accuracy on clean data. Being complementary to popular data augmentation methods, EWS consistently improves robustness when combined with these approaches. To highlight the flexibility of our approach, we combine EWS also with popular adversarial training methods resulting in improved adversarial robustness.
Enhancing Point Annotations with Superpixel and Confidence Learning Guided for Improving Semi-Supervised OCT Fluid Segmentation
Zhejiang Sci-Tech University（浙江理工大学）；Lishui University（丽水学院）；the Second Affiliated Hospital of Zhejiang University, College of Medicine（浙江大学医学院附属第二医院）；Communication University of Zhejiang（浙江传媒学院）；Hangzhou Dianzi University（杭州电子科技大学）；UT Southwestern Medical Center（德克萨斯大学西南医学中心）；Suzhou Research Institute of Shandong University（山东大学苏州研究院）
VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models
State Key Laboratory of Complex & Critical Software Environment, Beihang University（北京航空航天大学复杂与关键软件环境国家重点实验室）；School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）；City University of Macau（澳门城市大学）；Center on Frontiers of Computing Studies, School of Computer Science, Nat’l Eng. Research Center of Visual Technology, Peking University（北京大学计算机学院前沿计算研究中心、国家工程视觉技术研究中心）
Mitigating Bias: Enhancing Image Classification by Improving Model Explanations
Amirkabir University of Technology（阿米尔卡比尔理工大学）；Okinawa Institute of Science and Technology（冲绳科学技术大学院大学）；Institute for Research in Fundamental Sciences（基础科学研究所）
Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentation
Imperial College London（帝国理工学院）；University of Edinburgh（爱丁堡大学）；Fudan University（复旦大学）；City, University of London（伦敦城市大学）；Technical University of Munich（慕尼黑工业大学）
