Search Results for author: Hongcheng Huang

Found 2 papers, 2 papers with code

Using Feature Alignment Can Improve Clean Average Precision and Adversarial Robustness in Object Detection

1 code implementation8 Dec 2020 Weipeng Xu, Hongcheng Huang, Shaoyou Pan

In this paper, we propose that using feature alignment of intermediate layer can improve clean AP and robustness in object detection.

Adversarial Attack Adversarial Robustness +3

Robust and Accurate Object Detection via Self-Knowledge Distillation

1 code implementation14 Nov 2021 Weipeng Xu, Pengzhi Chu, Renhao Xie, Xiongziyan Xiao, Hongcheng Huang

In this paper, we propose Unified Decoupled Feature Alignment (UDFA), a novel fine-tuning paradigm which achieves better performance than existing methods, by fully exploring the combination between self-knowledge distillation and adversarial training for object detection.

Adversarial Robustness object-detection +3

Cannot find the paper you are looking for? You can Submit a new open access paper.