AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Transformer Meets Boundary Value Inverse Problems

Ruchi Guo, Shuhao Cao, Long Chen

ICLR 2023 · Architectures and efficiency › Attention and transformers · approach: Efficient image transformers · 9 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
replace U-Net convolutions with integral kernel attention (UIT)U-Net baseline · EIT benchmark tau=0Relative L2 error: 0.200 -> 0.163Improved
replace U-Net convolutions with integral kernel attention (UIT)U-Net baseline · EIT benchmark tau=0.05Relative L2 error: 0.341 -> 0.261Improved
use L=3 data pairs instead of L=1 (ablation)UIT · EIT benchmark tau=0Relative L2 error: 0.163 -> 0.147Improved
attention only on coarsest level (U-Net+Coarse Attn) (ablation)U-Net · EIT benchmark tau=0Relative L2 error: 0.200 -> 0.184 at tau=0; 0.341 -> 0.343 at tau=0.05Mixed
FNO-type global spectral kernels vs attention-based modelsFNO2d · EIT benchmark tau=0Relative L2 error: 0.318 vs 0.200 for U-NetHurt
UIT with softmax normalization (UIT+Softmax) vs UIT without softmax (ablation)UIT · EIT benchmark tau=0Relative L2 error: 0.159 vs 0.163 at tau=0; 0.269 vs 0.272 at tau=0.2Mixed

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