Spatial attention has been widely used to improve the performance of convolutional neural
networks. However, it has certain limitations. In this paper, we propose a new perspective on …

Convolutional neural networks are built upon the convolution operation, which extracts
informative features by fusing spatial and channel-wise information together within local …

Recently, the attention mechanism combining spatial and channel information has been
widely used in various deep convolutional neural networks (CNNs), proving its great …

While the use of bottom-up local operators in convolutional neural networks (CNNs)
matches well some of the statistics of natural images, it may also prevent such models from …

Neural networks rely on convolutions to aggregate spatial information. However, spatial
convolutions are expensive in terms of model size and computation, both of which grow …

In this paper, we propose a conceptually simple but very effective attention module for
Convolutional Neural Networks (ConvNets). In contrast to existing channel-wise and spatial …

A variety of attention mechanisms have been studied to improve the performance of various
computer vision tasks. However, the prior methods overlooked the significance of retaining …

Convolutional neural networks (CNNs) have demonstrated remarkable performance in
various computer vision tasks, such as image classification, semantic segmentation, and …

Vision Transformer (ViT) attains state-of-the-art performance in visual recognition, and the
variant, Local Vision Transformer, makes further improvements. The major component in …

Attention mechanisms have shown great success in computer vision. However, the
commonly used global average pooling in some implementations aggregates a three …