AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation

Yuanyi Zhong, Bodi Yuan, Hong Wu, Zhiqiang Yuan, Jian Peng, Yu-Xiong Wang

ICCV 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 212 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
add pixel contrastive loss to label consistency training (ablation)PC2Seg · VOC 2012 val, 1/8 labeled (ResNet-50)mIoU: 63.75 -> 64.63Improved
add label consistency loss to pixel contrastive loss (ablation)PC2Seg · VOC 2012 val, 1/8 labeled (ResNet-50)mIoU: 53.53 -> 64.63Improved
sample negatives from different images and debias with pseudo labels instead of uniformly (ablation)PC2Seg · VOC 2012 val, 1/8 labeled (ResNet-50)mIoU: 62.70 -> 64.63Improved
add Different Image constraint to uniform sampling (ablation)PC2Seg · VOC 2012 val, 1/8 labeled (ResNet-50)mIoU: 62.70 -> 63.33Improved
use ground-truth Oracle negatives instead of Diff+Pseudo sampling (ablation)PC2Seg · VOC 2012 val, 1/8 labeled (ResNet-50)mIoU: 64.63 -> 64.78No clear effect
increase number of negative pixels from 200 to 800 (ablation)PC2Seg · VOC 2012 val, 1/8 labeled (ResNet-50)mIoU: 64.63 -> 65.03Improved
use L2 label consistency loss instead of cross-entropy with pixel contrastive (ablation)PC2Seg · VOC 2012 val, 1/8 labeled (ResNet-50)mIoU: 58.47 -> 64.63Improved
use pixel contrastive instead of image-level contrastive loss (ablation)PC2Seg · VOC 2012 val, 1/8 labeled (ResNet-50)mIoU: 62.49 -> 64.63Improved
apply contrastive loss at Conv5 instead of Conv3 (ablation)PC2Seg · VOC 2012 val, 1/8 labeled (ResNet-50)mIoU: 60.70 -> 64.63Improved
apply contrastive loss at both Conv5 and Encoder instead of Conv5 alone (ablation)PC2Seg · VOC 2012 val, 1/8 labeled (ResNet-50)mIoU: 64.63 -> 64.59No clear effect
use separate projection heads instead of shared (ablation)PC2Seg · VOC 2012 val, 1/8 labeled (ResNet-50)mIoU: 63.97 -> 64.63Improved
start unlabeled losses from step 0 instead of delaying 2,000 steps (ablation)PC2Seg · VOC 2012 val, 1/8 labeled (ResNet-50)mIoU: 63.30 -> 64.63Improved

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