We show that combining human prior knowledge with end-to-end learning can improve the robustness of deep neural networks by introducing a part-based model for object classification. We believe that the richer form of annotation helps guide neural networks to learn more robust features without requiring more samples or larger models. Our model combines a part segmentation model with a tiny classifier and is trained end-to-end to simultaneously segment objects into parts and then classify the segmented object. Empirically, our part-based models achieve both higher accuracy and higher adversarial robustness than a ResNet-50 baseline on all three datasets. For instance, the clean accuracy of our part models is up to 15 percentage points higher than the baseline's, given the same level of robustness. Our experiments indicate that these models also reduce texture bias and yield better robustness against common corruptions and spurious correlations. The code is publicly available at https://github.com/chawins/adv-part-model.

翻译：我们证明，将人类先验知识与端到端学习相结合，通过引入用于目标分类的基于部件的模型，能够提升深度神经网络的鲁棒性。我们认为，更丰富的标注形式有助于引导神经网络学习更鲁棒的特征，而无需增加样本数量或扩大模型规模。我们的模型将部件分割模型与一个微型分类器相结合，并以端到端方式训练，同时实现将目标分割为部件以及对分割后的目标进行分类。实验表明，我们的基于部件的模型在所有三个数据集上均比ResNet-50基线取得了更高的准确率和对抗鲁棒性。例如，在相同鲁棒性水平下，我们的部件模型的干净准确率比基线高出多达15个百分点。实验还表明，这些模型减少了纹理偏差，并对常见损坏和虚假相关性具有更好的鲁棒性。代码已公开于https://github.com/chawins/adv-part-model。