Papers › Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for...

Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration

1 Jan 2024CVPR 2024 1archive 2025-07-28

Shihao Zhou, Duosheng Chen, Jinshan Pan, Jinglei Shi, Jufeng Yang

Transformer-based approaches have achieved promising performance in image restoration tasks given their ability to model long-range dependencies which is crucial for recovering clear images. Though diverse efficient attention mechanism designs have addressed the intensive computations associated with using transformers they often involve redundant information and noisy interactions from irrelevant regions by considering all available tokens. In this work we propose an Adaptive Sparse Transformer (AST) to mitigate the noisy interactions of irrelevant areas and remove feature redundancy in both spatial and channel domains. AST comprises two core designs i.e. an Adaptive Sparse Self-Attention (ASSA) block and a Feature Refinement Feed-forward Network (FRFN). Specifically ASSA is adaptively computed using a two-branch paradigm where the sparse branch is introduced to filter out the negative impacts of low query-key matching scores for aggregating features while the dense one ensures sufficient information flow through the network for learning discriminative representations. Meanwhile FRFN employs an enhance-and-ease scheme to eliminate feature redundancy in channels enhancing the restoration of clear latent images. Experimental results on commonly used benchmarks have demonstrated the versatility and competitive performance of our method in several tasks including rain streak removal real haze removal and raindrop removal. The code and pre-trained models are available at https://github.com/joshyZhou/AST.

Paper PDF Code

Code

joshyzhou/ast officialmentioned in paperpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Restoration Rain Removal Raindrop Removal

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position Encodings Adam Attention Attention Dropout BPE Cosine Annealing Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Linear Warmup With Cosine Annealing Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Sparse Transformer Transformer Weight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections