most citedAdversarial Contrastive Distillation with Adaptive Denoising

1 citations · 3 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV2024

Self-Cooperation Knowledge Distillation for Novel Class Discovery

Yuzheng Wang, Zhaoyu Chen, Dingkang Yang +2

Novel Class Discovery (NCD) aims to discover unknown and novel classes in an unlabeled set by leveraging knowledge already learned about known classes. Existing works focus on inst…

cs.CV2024

De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts

Yuzheng Wang, Dingkang Yang, Zhaoyu Chen +5

Data-Free Knowledge Distillation (DFKD) is a promising task to train high-performance small models to enhance actual deployment without relying on the original training data. Exist…

cs.MM20231 cited

Learning Causality-inspired Representation Consistency for Video Anomaly Detection

Yang Liu, Zhaoyang Xia, Mengyang Zhao +7

Video anomaly detection is an essential yet challenging task in the multimedia community, with promising applications in smart cities and secure communities. Existing methods attem…

cs.CV20231 cited

AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception

Dingkang Yang, Shuai Huang, Zhi Xu +12

Driver distraction has become a significant cause of severe traffic accidents over the past decade. Despite the growing development of vision-driven driver monitoring systems, the…

cs.CV2023

Explicit and Implicit Knowledge Distillation via Unlabeled Data

Yuzheng Wang, Zuhao Ge, Zhaoyu Chen +4

Data-free knowledge distillation is a challenging model lightweight task for scenarios in which the original dataset is not available. Previous methods require a lot of extra compu…

cs.CV20231 cited

Adversarial Contrastive Distillation with Adaptive Denoising

Yuzheng Wang, Zhaoyu Chen, Dingkang Yang +4

Adversarial Robustness Distillation (ARD) is a novel method to boost the robustness of small models. Unlike general adversarial training, its robust knowledge transfer can be less…