1 code implementation • 14 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.
1 code implementation • 8 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.