AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Uncertainty-Driven Spectral Compressive Imaging with Spatial-Frequency Transformer

Lintao Peng, Siyu Xie, Liheng Bian

ECCV 2024 · Architectures and efficiency › Attention and transformers · approach: Efficient image transformers · 3 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 FWSA to the baseline (ablation)Specformer baseline · KAIST (trained on CAVE)PSNR (dB): 31.08 -> 35.97Improved
add LWSA to the baseline (ablation)Specformer baseline · KAIST (trained on CAVE)PSNR (dB): 31.08 -> 33.34Improved
combine LWSA and FWSA in parallel instead of serially (ablation)SF-block · KAIST (trained on CAVE)PSNR (dB): 37.58 -> 39.82Improved
parallel instead of serial design reduces cost (ablation)SF-block · KAIST (trained on CAVE)Params / GFLOPs: 2.82M -> 2.48M; 46.73 -> 39.85Improved
add uncertainty-driven loss (two-stage training) (ablation)Specformer · KAIST (trained on CAVE)PSNR (dB): 39.82 -> 40.61Improved
add uncertainty-driven loss (ablation)Specformer · KAIST (trained on CAVE)Params / GFLOPs at test time: 2.48M, 39.85 unchangedNo clear effect
two-stage UDL trainingSpecformer · training costtraining time: about +30%Hurt

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