AI Paper Atlas

Research map / Detection and segmentation / CNN features

SegFormer: A Topic Segmentation Model with Controllable Range of Attention

Haitao Bai, Pinghui Wang, Ruofei Zhang, Zhou Su

AAAI 2023 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 16 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
Use SegFormer instead of Transformer2WIKI-SECTION · En Disease, De Disease, En City, and De CityPk: 18.8 -> 17.6; 16.0 -> 14.9; 9.1 -> 8.2; 7.3 -> 6.8Improved
Add topic classification loss to guide context range (ablation)SegFormer · WIKI-SECTIONPk: 22.7 -> 17.6; 18.7 -> 14.9; 8.6 -> 8.2; 7.1 -> 6.8Improved
Add the sentence contextualization encoder (ablation)SegFormer · WIKI-SECTIONPk: 23.3 -> 17.6; 18.6 -> 14.9; 10.6 -> 8.2; 11.1 -> 6.8Improved
Add training and iterative inference strategy (ablation)SegFormer · WIKI-SECTIONPk: 18.4 -> 17.6; 15.6 -> 14.9; 8.6 -> 8.2; 7.2 -> 6.8Improved
Add context aggregator along with training and inference strategy (ablation)SegFormer · WIKI-SECTIONPk: 23.7 -> 17.6; 19.9 -> 14.9; 9.0 -> 8.2; 8.2 -> 6.8Improved
Add topic loss, context aggregator, and training/inference strategy (ablation)SegFormer · WIKI-SECTIONPk: 26.6 -> 17.6; 22.9 -> 14.9; 9.7 -> 8.2; 8.5 -> 6.8Improved
Use SegFormer rather than the strongest listed baselineWIKI-SECTION transfer datasets · WIKI-50, Cities, Elements, Clinical BooksPk: 29.3 -> 25.3; 16.1 -> 15.2; 45.2 -> 49.4; 36.9 -> 28.6Mixed

Later papers that compared with this method

33 later accepted papers report SegFormer as a baseline in their results tables; 31 of them report a better number on most of the results they share with it.

25 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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