AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Bias-Resilient Weakly Supervised Semantic Segmentation Using Normalizing Flows

Xianglin Qiu, Xiaoyang Wang, Zhen Zhang, Jimin Xiao

ICCV 2025 · Detection and segmentation › Weakly supervised detection and segmentation · approach: CAM refinement and prototypes · 2 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 BRNF (normalizing-flow GMM calibration, feature sampling, denoising) to CLIP-ESCLIP-ES · PASCAL VOC 2012 train (seed CAM)mIoU: 70.8 -> 72.1Improved
add BRNF to CLIP-ESCLIP-ES · PASCAL VOC 2012 train (pseudo-label mask)mIoU: 75.0 -> 79.2Improved
add BRNF to SFCSFC · PASCAL VOC 2012 train (seed CAM)mIoU: 64.7 -> 70.7Improved
add BRNF to SFCSFC · PASCAL VOC 2012 train (pseudo-label mask)mIoU: 73.7 -> 77.4Improved
add BRNF to CLIP-ES then train DeepLabV2CLIP-ES · PASCAL VOC 2012 valmIoU: 71.1 -> 75.9Improved
add BRNF to CLIP-ES then train DeepLabV2CLIP-ES · PASCAL VOC 2012 testmIoU: 71.4 -> 76.2Improved
add BRNF to CLIP-ES then train DeepLabV2CLIP-ES · MS COCO 2014 valmIoU: 45.4 -> 47.9Improved
add BRNF to SFC then train DeepLabV2SFC · PASCAL VOC 2012 valmIoU: 71.2 -> 74.8Improved
add BRNF to SFC then train DeepLabV2SFC · MS COCO 2014 valmIoU: 46.8 -> 47.7Improved
use CLIP-ES + BRNF instead of PSDPM guidancePSDPM · PASCAL VOC 2012 valmIoU: 74.1 -> 75.9Improved

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