3 papers
cs.CV2026
FedDBP: Enhancing Federated Prototype Learning with Dual-Branch Features and Personalized Global Fusion
Ningzhi Gao, Siquan Huang, Leyu Shi +1
Federated prototype learning (FPL), as a solution to heterogeneous federated learning (HFL), effectively alleviates the challenges of data and model heterogeneity.However, existing…
cs.CV2026
BackdoorIDS: Zero-shot Backdoor Detection for Pretrained Vision Encoder
Siquan Huang, Yijiang Li, Ningzhi Gao +3
Self-supervised and multimodal vision encoders learn strong visual representations that are widely adopted in downstream vision tasks and large vision-language models (LVLMs). Howe…
cs.LG2024
Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term
Yun Yue, Jiadi Jiang, Zhiling Ye +3
Deep Neural Networks (DNNs) generalization is known to be closely related to the flatness of minima, leading to the development of Sharpness-Aware Minimization (SAM) for seeking fl…