Multi-view Feature Augmentation with Adaptive Class Activation Mapping

arXiv:2206.12943v4 Announce Type: replace
Abstract: 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 …

abstract arxiv augmentation boost class classification cs.cv diverse ensemble exploits extract feature features gap global image mapping performance pooling sample type view