Attention Block Based on Binary Pooling

Image classification has become highly significant in the field of computer vision due to its wide array of applications. In recent years, Convolutional Neural Networks (CNN) have emerged as potent tools for addressing this task. Attention mechanisms offer an effective approach to enhance the accuracy of image classification. Despite Global Average Pooling (GAP) being a crucial component of traditional attention mechanisms, it only computes the average of spatial elements in each channel, failing to capture the complete range of feature information, resulting in fewer and less expressive features. To address this limitation, we propose a novel pooling operation named Binary Pooling and integrate it into the attention block. Binary pooling combines both GAP and Global Max Pooling (GMP), obtaining a more comprehensive feature vector by extracting average and maximum values, thereby enriching the diversity of extracted image features. Furthermore, to further enhance the extraction of image features, dilation operations and pointwise convolutions are applied on the channel-wise. The proposed attention block is simple yet highly effective. Upon integration into ResNet18/50 models, it leads to accuracy improvements of 2.02%/0.63% on ImageNet.

Automated summary

Image classification is crucial in computer vision with a wide range of applications. This study proposes a novel pooling operation, named Binary Pooling, which combines Global Average Pooling (GAP) and Global Max Pooling (GMP) to extract more comprehensive image features. By applying dilation operations and pointwise convolutions, the extraction of image features is further enhanced. Experimental results show that integrating this attention block into ResNet18/50 models improves accuracy on ImageNet.