2.4k citations · 3.7k across the 27 of their papers we have counts for
6 papers · 1 filter
Improving Robust Fairness via Balance Adversarial Training
Chunyu Sun, Chenye Xu, Chengyuan Yao +5
Adversarial training (AT) methods are effective against adversarial attacks, yet they introduce severe disparity of accuracy and robustness between different classes, known as the…
Universal Backdoor Attacks Detection via Adaptive Adversarial Probe
Yuhang Wang, Huafeng Shi, Rui Min +5
Extensive evidence has demonstrated that deep neural networks (DNNs) are vulnerable to backdoor attacks, which motivates the development of backdoor attacks detection. Most detecti…
DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection
Gang Li, Xiang Li, Yujie Wang +3
The Mean-Teacher (MT) scheme is widely adopted in semi-supervised object detection (SSOD). In MT, the sparse pseudo labels, offered by the final predictions of the teacher (e.g., a…
Learning Locality and Isotropy in Dialogue Modeling
Han Wu, Haochen Tan, Mingjie Zhan +4
Existing dialogue modeling methods have achieved promising performance on various dialogue tasks with the aid of Transformer and the large-scale pre-trained language models. Howeve…
CoupleFace: Relation Matters for Face Recognition Distillation
Jiaheng Liu, Haoyu Qin, Yichao Wu +3
Knowledge distillation is an effective method to improve the performance of a lightweight neural network (i.e., student model) by transferring the knowledge of a well-performed neu…
PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection
Gang Li, Xiang Li, Yujie Wang +3
In this paper, we delve into two key techniques in Semi-Supervised Object Detection (SSOD), namely pseudo labeling and consistency training. We observe that these two techniques cu…