AI Paper Atlas

Research map / Detection and segmentation / CNN features

Region-Aware Contrastive Learning for Semantic Segmentation

Hanzhe Hu, Jinshi Cui, Liwei Wang

ICCV 2021 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 148 citations (OpenAlex)

Read the paper

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 intra-image region-aware contrastive loss to CE (ablation)DeepLabV3 ResNet-50 · Cityscapes val (DeepLabV3 R50 ablation)mIoU: 76.4 -> 77.5Improved
extend contrast to inter-image with memory bank (ablation)RegionContrast DeepLabV3 ResNet-50 · Cityscapes val (DeepLabV3 R50 ablation)mIoU: 77.5 -> 79.6Improved
build region centers with easy and hard positives instead of direct average (ablation)RegionContrast · Cityscapes val (DeepLabV3 R50 ablation)mIoU: 78.2 -> 78.8Improved
weight easy and hard positives (dynamic sampling) (ablation)RegionContrast · Cityscapes val (DeepLabV3 R50 ablation)mIoU: 78.8 -> 79.6Improved
add memory bank of size 1000 (ablation)RegionContrast · Cityscapes val (DeepLabV3 R50 ablation)mIoU: 77.5 -> 78.5Improved
increase memory bank size from 1000 to 2000 (ablation)RegionContrast · Cityscapes val (DeepLabV3 R50 ablation)mIoU: 78.5 -> 79.1Improved
increase memory bank size from 2000 to full training set 2975 (ablation)RegionContrast · Cityscapes val (DeepLabV3 R50 ablation)mIoU: 79.1 -> 79.6Improved
add RegionContrast to DeepLabV3 ResNet-50DeepLabV3 · Cityscapes valmIoU: 76.4 -> 79.6Improved
add RegionContrast to DeepLabV3 ResNet-101DeepLabV3 · Cityscapes valmIoU: 79.0 -> 81.3Improved
add RegionContrast to HRNetV2-W48HRNetV2 · Cityscapes valmIoU: 80.4 -> 81.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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