Dual Aggregation Transformer for Image Super-Resolution

Yulun Zhang, Xiaokang Yang, Jinjin Gu, Linghe Kong, Zheng Chen, Yu Fisher

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 17 functions out of this paper's own repositories and ran 9 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• zhengchen1999/dat — marked official in Papers with Code; named in the paper
• zhengchen1999/DAT

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Transformer has recently gained considerable popularity in low-level vision tasks, including image superresolution (SR). These networks utilize self-attention along different dimensions, spatial or channel, and achieve impressive performance. This inspires us to combine the two dimensions in Transformer for a more powerful representation capability. Based on the above idea, we propose a novel Transformer model, Dual Aggregation Transformer (DAT), for image SR. Our DAT aggregates features across spatial and channel dimensions, in the interblock and intra-block dual manner. Specifically, we alternately apply spatial and channel self-attention in consecutive Transformer blocks. The alternate strategy enables DAT to capture the global context and realize inter-block feature aggregation. Furthermore, we propose the adaptive interaction module (AIM) and the spatial-gate feed-forward network (SGFN) to achieve intra-block feature aggregation. AIM complements two self-attention mechanisms from corresponding dimensions. Meanwhile, SGFN introduces additional non-linear spatial information in the feed-forward network. Extensive experiments show that our DAT surpasses current methods. Code and models are obtainable at https://github.com/zhengchen1999/DAT.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2308.03364")
get_code_for_paper("2308.03364")
have("2308.03364")

Connect an agent — have() is free.