论文标题
极值保留网络
Extreme Value Preserving Networks
论文作者
论文摘要
最近的证据表明，卷积神经网络（CNN）对纹理有偏见，因此CNN对对抗性对纹理的逆向不舒适，而传统的强大视觉特征（例如SIFT（Scale-In-Variant特征变换））的设计旨在在杂乱无章的噪音中添加大量的噪音，与Mimic的人类感知性质相处。本文旨在利用SIFT的良好特性来翻新CNN体系结构，以提高准确性和鲁棒性。我们从SIFT借用规模的高度价值思想，并提出了极值保留网络（EVPNET）。实验表明，EVPNET可以比常规CNN获得相似或更好的准确性，同时即使没有对抗性训练，也可以在一组对抗性攻击（FGSM，PGD等）上获得更好的鲁棒性。
Recent evidence shows that convolutional neural networks (CNNs) are biased towards textures so that CNNs are non-robust to adversarial perturbations over textures, while traditional robust visual features like SIFT (scale-invariant feature transforms) are designed to be robust across a substantial range of affine distortion, addition of noise, etc with the mimic of human perception nature. This paper aims to leverage good properties of SIFT to renovate CNN architectures towards better accuracy and robustness. We borrow the scale-space extreme value idea from SIFT, and propose extreme value preserving networks (EVPNets). Experiments demonstrate that EVPNets can achieve similar or better accuracy than conventional CNNs, while achieving much better robustness on a set of adversarial attacks (FGSM,PGD,etc) even without adversarial training.
