We propose an end-to-end-trainable feature augmentation module built for image classification that extracts and exploits multi-view local features to boost model performance. Different from using global average pooling (GAP) to extract vectorized features from only the global view, we propose to sample and ensemble diverse multi-view local features to improve model robustness. To sample class-representative local features, we incorporate a simple auxiliary classifier head (comprising only one 1$\times$1 convolutional layer) which efficiently and adaptively attends to class-discriminative local regions of feature maps via our proposed AdaCAM (Adaptive Class Activation Mapping). Extensive experiments demonstrate consistent and noticeable performance gains achieved by our multi-view feature augmentation module.

本论文提出了一种端到端可训练的特征增强模块，用于图像分类，它提取并利用多视角局部特征来提高模型性能，并结合自适应类别激活映射（AdaCAM）以及辅助分类器头，以通过采样类典型的局部特征来有效地关注类别鉴别性局部区域，进而提高模型对抗性和鲁棒性。大量实验证明，我们的多视角特征增强模块具有一致且显著的性能提升。

自适应类别激活映射多视图特征增强