论文标题
通过最大程度的判别特征来实现稳健的细粒识别
Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features
论文作者
论文摘要
对抗性攻击已被广泛研究以进行一般分类任务，但在细粒度识别的背景下仍未探索，在这种情况下，类间相似性有助于攻击者的任务。在本文中，我们确定了细粒度识别网络中不同类别的潜在表示的接近性，这是对抗攻击成功的关键因素。因此，我们引入了一种基于注意力的正则化机制，该机制可最大程度地分开不同类别的歧视性潜在特征，同时最大程度地减少非歧视区域对最终类预测的贡献。正如我们的实验所证明的那样，这使我们能够显着提高对对抗性攻击，匹配甚至超过对抗性训练的鲁棒性，而无需访问对抗性样本。
Adversarial attacks have been widely studied for general classification tasks, but remain unexplored in the context of fine-grained recognition, where the inter-class similarities facilitate the attacker's task. In this paper, we identify the proximity of the latent representations of different classes in fine-grained recognition networks as a key factor to the success of adversarial attacks. We therefore introduce an attention-based regularization mechanism that maximally separates the discriminative latent features of different classes while minimizing the contribution of the non-discriminative regions to the final class prediction. As evidenced by our experiments, this allows us to significantly improve robustness to adversarial attacks, to the point of matching or even surpassing that of adversarial training, but without requiring access to adversarial samples.
