AI Paper Atlas

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

ConformalSAM: Unlocking the Potential of Foundational Segmentation Models in Semi-Supervised Semantic Segmentation with Conformal Prediction

Danhui Chen, Ziquan Liu, Chuxi Yang, Dan Wang, Yan Yan, Yi Xu, Xiangyang Ji

ICCV 2025 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 6 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 raw SEEM masks as pseudo-labels for unlabeled dataSegFormer-B5 label-only · PASCAL VOC 2012 original, 1/16 (92)mIoU: 50.65 -> 42.00Hurt
use raw SEEM masks as pseudo-labels for unlabeled dataSegFormer-B5 label-only · ADE20K, 1/16 (1263)mIoU: 28.76 -> 21.45Hurt
use raw SEEM masks as pseudo-labels (smallest ADE20K split)SegFormer-B5 label-only · ADE20K, 1/64 (316)mIoU: 18.83 -> 20.53Improved
add conformal prediction calibration to SEEM pseudo-labels (ablation)ConformalSAM · PASCAL VOC 2012 originalmIoU: 42.00 -> 78.09Improved
add self-reliance training in stage II (ablation)ConformalSAM · PASCAL VOC 2012 originalmIoU: 78.09 -> 81.21Improved
add self-reliance training without CP (ablation)SEEM pseudo-labels · PASCAL VOC 2012 originalmIoU: 42.00 -> 65.94Improved
use mis-coverage rate alpha 0.05 instead of 0.1 (ablation)pixel-wise CP · PASCAL VOC 2012 originalmIoU: 74.31 -> 78.09Improved
use mis-coverage rate alpha 0.05 instead of 0.01 (ablation)pixel-wise CP · PASCAL VOC 2012 originalmIoU: 68.01 -> 78.09Improved
use pixel-wise CP instead of image-level CP (ablation)ConformalSAM · PASCAL VOC 2012 originalmIoU: 75.54 -> 78.09Improved
add class-conditional label selection to vanilla CP (ablation)ConformalSAM · PASCAL VOC 2012 originalmIoU: 34.11 mIoU averageImproved
start self-reliance training at epoch 60 instead of 10 (ablation)ConformalSAM · PASCAL VOC 2012 originalmIoUImproved
combine ConformalSAM with AllSpark instead of AllSpark aloneAllSpark · PASCAL VOC 2012 originalmIoU: 76.07 -> 80.69Improved

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