1 code implementation • 23 Sep 2023 • PengFei Liu, Weibo Wang, Yuhan Guo, Jiubin Tan
Distinctly, for alleviating the inconsistency of classification score and localization quality during training and inference, under which some predictions with low classification scores but high LQE scores will impair the performance, instead of separately and independently setting, we embedded LQE branch into classification branch, producing a joint classification-localization-quality representation.
no code implementations • 4 Jul 2022 • Yaguan Qian, Yuqi Wang, Bin Wang, Zhaoquan Gu, Yuhan Guo, Wassim Swaileh
Extensive experiments conducted on the MINIST and CIFAR-10 datasets show that our adversarial learning with second-order adversarial examples outperforms other fisrt-order methods, which can improve the model robustness against a wide range of attacks.