atlas

Research map / Detection and segmentation / CNN features

EDTER: Edge Detection With Transformer

CVPR 2022 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 251 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use EDTER with multi-scale testing and extra PASCAL VOC training dataEDTER · BSDS500 testODS: 0.824 -> 0.848Helped
Use EDTER instead of BDCNedge detection · NYUDv2ODS: 0.748 -> 0.774Helped
Use EDTER instead of BDCNedge detection · Multicue BoundaryODS: .836 (0.001) -> .861 (0.003)Helped
Replace SETR-MLA with BiMLA (ablation)EDTER Stage I · BSDS500ODS: 0.790 -> 0.817Helped
Replace SETR-MLA with BiMLA (ablation)EDTER Stage II with FFM · BSDS500AP: 0.848 -> 0.880Helped
Add the second stage with 8×8 patches (ablation)EDTER Stage I · BSDS500ODS: 0.817 -> 0.824Helped
Add FFM to fuse global and local stage features (ablation)EDTER Stage II · BSDS500AP: 0.867 -> 0.880Helped
Use 4×4 rather than 8×8 patches in Stage II (ablation)EDTER · BSDS500ODS: 0.824 -> 0.825Helped
Add Stage III with 4×4 patches (ablation)EDTER · BSDS500ODS: 0.824 -> 0.826Helped

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