AI Paper Atlas

Research map / Detection and segmentation / CNN features

Learning Statistical Texture for Semantic Segmentation

Lanyun Zhu, Deyi Ji, Shiping Zhu, Weihao Gan, Wei Wu, Junjie Yan

CVPR 2021 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 136 citations (OpenAlex)

Check 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 STLNet instead of SFNetCityscapes segmentation with ResNet-101 · Cityscapes testmIoU (%): 81.8 -> 82.3Improved
Use STLNet instead of CaC-NetPASCAL Context segmentation with ResNet-101 · PASCAL Context validationmIoU (%): 55.4 -> 55.8Improved
Use STLNet instead of CPNetADE20K segmentation with ResNet-101 · ADE20K validationmIoU (%): 46.27 -> 46.48Improved
Add shallow layer feature fusion (ablation)ResNet-101 segmentation model · CityscapesmIoU (%): 76.4 -> 77.0Improved
Add TEM to a model with shallow layer feature fusion (ablation)ResNet-101 + SLF · CityscapesmIoU (%): 77.0 -> 80.3Improved
Add PTFEM to a model with shallow layer feature fusion (ablation)ResNet-101 + SLF · CityscapesmIoU (%): 77.0 -> 80.0Improved
Add TEM and PTFEM to a model with shallow layer feature fusion (ablation)ResNet-101 + SLF · CityscapesmIoU (%): 77.0 -> 80.9Improved
Add TEM and PTFEM to ResNet-101 + ASPP + SLF (ablation)ResNet-101 + ASPP + SLF · CityscapesmIoU (%): 79.3 -> 81.5Improved
Add the learned graph and feature reassignment in TEM (ablation)ResNet-101 + ASPP + SLF + TEM · CityscapesmIoU (%): 79.9 -> 80.9Improved
Use multiple PTFEM scales instead of any one tested scale (ablation)STLNet · CityscapesmIoU (%): 81.0, 81.0, 81.1, 81.2 -> 81.5Improved
Set 1-d QCO to 128 quantization levels (ablation)STLNet with TEM and PTFEM · CityscapesmIoU (%): 81.5Improved
Increase quantization levels beyond 128 (ablation)STLNet with TEM and PTFEM · CityscapesmIoU (%)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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