WMSA-WBS: Efficient Wave Multi-Head Self-Attention with Wavelet Bottleneck

WMSA-WBS:基于小波瓶颈的高效波浪多头自注意力机制

阅读:1

Abstract

The critical component of the vision transformer (ViT) architecture is multi-head self-attention (MSA), which enables the encoding of long-range dependencies and heterogeneous interactions. However, MSA has two significant limitations: its limited ability to capture local features and its high computational costs. To address these challenges, this paper proposes an integrated multi-head self-attention approach with a bottleneck enhancement structure, named WMSA-WBS, which mitigates the aforementioned shortcomings of conventional MSA. Different from existing wavelet-enhanced ViT variants that mainly focus on the isolated wavelet decomposition in the attention layer, WMSA-WBS introduces a co-design of wavelet-based frequency processing and bottleneck optimization, achieving more efficient and comprehensive feature learning. Within WMSA-WBS, the proposed wavelet multi-head self-attention (WMSA) approach is combined with a novel wavelet bottleneck structure to capture both global and local information across the spatial, frequency, and channel domains. Specifically, this module achieves these capabilities while maintaining low computational complexity and memory consumption. Extensive experiments demonstrate that ViT models equipped with WMSA-WBS achieve superior trade-offs between accuracy and model complexity across various vision tasks, including image classification, object detection, and semantic segmentation.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。