0

Attention in Attention Network for Image Super-Resolution

The study quantifies and visualizes attention mechanisms in single-image super-resolution, proposing an Attention in Attention Network (A$^2$N) that dynamically adjusts attention to improve efficiency and performance.

Year
2021
Venue
attention-in-attention-network-for-image-1
Authors
3
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2104.09497v3ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Convolutional neural networks have allowed remarkable advances in single image super-resolution (SISR) over the last decade. Among recent advances in SISR, attention mechanisms are crucial for high-performance SR models. However, the attention mechanism remains unclear on why and how it works in SISR. In this work, we attempt to quantify and visualize attention mechanisms in SISR and show that not all attention modules are equally beneficial. We then propose attention in attention network (A$^2$N) for more efficient and accurate SISR. Specifically, A$^2$N consists of a non-attention branch and a coupling attention branch. A dynamic attention module is proposed to generate weights for these two branches to suppress unwanted attention adjustments dynamically, where the weights change adaptively according to the input features. This allows attention modules to specialize to beneficial examples without otherwise penalties and thus greatly improve the capacity of the attention network with few parameters overhead. Experimental results demonstrate that our final model A$^2$N could achieve superior trade-off performances comparing with state-of-the-art networks of similar sizes. Codes are available at https://github.com/haoyuc/A2N.

Authors

3