AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction

Yuanhao Cai, Jing Lin, Xiaowan Hu, Haoqian Wang, Xin Yuan, Yulun Zhang, Radu Timofte, Luc Van Gool

ECCV 2022 · Architectures and efficiency › Attention and transformers · approach: Efficient image transformers · 187 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SAH-MSA hashing attention (ablation)CST-M baseline · KAIST 10 scenes ablation (CST-M base)PSNR (dB): 32.57 -> 35.53Improved
add SASM patch screening on top of SAH-MSA (ablation)CST-M · KAIST 10 scenes ablation (CST-M base)FLOPS (G): 24.60 -> 16.91Improved
add SASM patch screening on top of SAH-MSA (ablation)CST-M · KAIST 10 scenes ablation (CST-M base)PSNR (dB): 35.53 -> 35.31Hurt
use SASM instead of random sparsity (ablation)CST-M · KAIST 10 scenes ablation (CST-M base)PSNR (dB): 34.37 -> 35.31Improved
use SASM instead of uniform sparsity (ablation)CST-M · KAIST 10 scenes ablation (CST-M base)PSNR (dB): 34.33 -> 35.31Improved
use SAH-MSA instead of G-MSA (ablation)CST-M · KAIST 10 scenes ablation (CST-M base)PSNR (dB): 35.04 -> 35.53Improved
use SAH-MSA instead of W-MSA (ablation)CST-M · KAIST 10 scenes ablation (CST-M base)PSNR (dB): 35.02 -> 35.53Improved
use SAH-MSA instead of Swin-MSA (ablation)CST-M · KAIST 10 scenes ablation (CST-M base)PSNR (dB): 35.12 -> 35.53Improved
use SAH-MSA instead of S-MSA (ablation)CST-M · KAIST 10 scenes ablation (CST-M base)PSNR (dB): 35.21 -> 35.53Improved
restrict hash clustering to local patches rather than global image (ablation)CST-M · KAIST 10 scenes ablation (CST-M base)PSNR (dB): 35.33 -> 35.53Improved
increase sparsity ratio sigma beyond 50% (ablation)CST-M · KAIST 10 scenesPSNR (dB)Hurt
increase hashing rounds R from 1 to 2 and beyond (ablation)CST-M · KAIST 10 scenesPSNR (dB)Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy