AI Paper Atlas

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

C3-SemiSeg: Contrastive Semi-Supervised Segmentation via Cross-Set Learning and Dynamic Class-Balancing

Yanning Zhou, Hang Xu, Wei Zhang, Bin Gao, Pheng-Ann Heng

ICCV 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 80 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 consistency loss with augmentation (versus supervised baseline plus contrast only) (ablation)C3-SemiSeg · Cityscapes val (1/30, 1/8, 1/4 labeled)mIoU: 48.8 -> 54.4, 60.2 -> 63.3, 64.4 -> 65.8Improved
add pixel-wise contrastive loss on top of consistency (ablation)C3-SemiSeg · Cityscapes val (1/30, 1/8, 1/4 labeled)mIoU: 54.4 -> 55.0, 63.3 -> 63.7, 65.8 -> 66.4Improved
apply contrastive loss only to labeled features DL (ablation)C3-SemiSeg · Cityscapes val (1/30, 1/8, 1/4 labeled)mIoU: 54.4 -> 53.5, 63.3 -> 61.9, 65.7 -> 65.8Hurt
apply contrastive loss to unlabeled features DU (ablation)C3-SemiSeg · Cityscapes val (1/30, 1/8, 1/4 labeled)mIoU: 54.4 -> 54.6, 63.3 -> 63.5, 65.7 -> 66.4Improved
apply contrastive loss across DL and DU with segmentation-aware sampling (ablation)C3-SemiSeg · Cityscapes val (1/30, 1/8, 1/4 labeled)mIoU: 54.6 -> 55.0, 64.2 -> 63.7, 65.8 -> 66.4Improved
use strong augmentation with RandAugment on both teacher and student (ablation)consistency regularization · Cityscapes val (1/30, 1/8, 1/4 labeled)mIoU: 45.0 -> 43.2, 55.7 -> 54.8, 60.8 -> 57.1Hurt
use weak augmentation on both networks (ablation)consistency regularization · Cityscapes val (1/30, 1/8, 1/4 labeled)mIoU: 45.0 -> 50.6, 55.7 -> 59.3, 60.8 -> 62.0Improved
asymmetric augmentation: weak for teacher, strong for student (ablation)consistency regularization · Cityscapes val (1/30, 1/8, 1/4 labeled)mIoU: 50.6 -> 53.9, 59.3 -> 63.2, 62.0 -> 64.8Improved
add RandAugment to the student's strong augmentation (ablation)consistency regularization · Cityscapes val (1/30, 1/8, 1/4 labeled)mIoU: 53.9 -> 54.4, 63.2 -> 63.3, 64.8 -> 65.8Improved
add intra-set region-level data mixing (ablation)C3-SemiSeg · Cityscapes val (1/30, 1/8, 1/4 labeled)mIoU: 51.1 -> 53.3, 60.7 -> 62.4, 63.3 -> 65.2Improved
mix across labeled and unlabeled sets instead of within sets (ablation)C3-SemiSeg · Cityscapes val (1/30, 1/8, 1/4 labeled)mIoU: 53.3 -> 54.4, 62.4 -> 63.3, 65.2 -> 65.8Improved
add DCRS (s=0.8 versus s=1.0, i.e. no selection) (ablation)C3-SemiSeg · Cityscapes val (1/8 labeled)mIoU: 62.8 -> 63.3Improved

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