BA^2M: A Batch Aware Attention Module for Image Classification
This work addresses a limitation in attention mechanisms for image classification, offering a lightweight module that enhances feature representation across samples, though it appears incremental as it builds on existing attention paradigms.
The paper tackles the problem of existing attention mechanisms in CNNs focusing only on intra-sample features by proposing a batch aware attention module (BA^2M) that also considers inter-sample discrimination, resulting in performance boosts on CIFAR-100 and ImageNet-1K for image recognition tasks, outperforming classical attention methods and loss-based re-weighting approaches.
The attention mechanisms have been employed in Convolutional Neural Network (CNN) to enhance the feature representation. However, existing attention mechanisms only concentrate on refining the features inside each sample and neglect the discrimination between different samples. In this paper, we propose a batch aware attention module (BA2M) for feature enrichment from a distinctive perspective. More specifically, we first get the sample-wise attention representation (SAR) by fusing the channel, local spatial and global spatial attention maps within each sample. Then, we feed the SARs of the whole batch to a normalization function to get the weights for each sample. The weights serve to distinguish the features' importance between samples in a training batch with different complexity of content. The BA2M could be embedded into different parts of CNN and optimized with the network in an end-to-end manner. The design of BA2M is lightweight with few extra parameters and calculations. We validate BA2M through extensive experiments on CIFAR-100 and ImageNet-1K for the image recognition task. The results show that BA2M can boost the performance of various network architectures and outperforms many classical attention methods. Besides, BA2M exceeds traditional methods of re-weighting samples based on the loss value.