AI Paper Atlas

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

Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentation

Haochen Wang, Yuchao Wang, Yujun Shen, Junsong Fan, Yuxi Wang, Zhaoxiang Zhang

IJCV 2024 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 17 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 unreliable instead of reliable pixels as negative keys (with labeled) (ablation)Ours · PASCAL VOC 2012 blender, 1/4 (2646) labeledmIoU: 77.35 -> 80.21Improved
add reliable pixels to unreliable negative keys (ablation)Ours · PASCAL VOC 2012 blender, 1/4 (2646) labeledmIoU: 80.21 -> 77.57Hurt
add vanilla contrastive loss alone (ablation)Ours · PASCAL VOC 2012 blender, 1/4 (2646) labeledmIoU: 77.33 -> 77.08Hurt
add category-wise memory bank, PRT and unreliable negatives to contrastive loss (ablation)Ours · PASCAL VOC 2012 blender, 1/4 (2646) labeledmIoU: 77.08 -> 78.49Improved
add dynamic partition adjustment with unreliable negatives (ablation)Ours · PASCAL VOC 2012 blender, 1/4 (2646) labeledmIoU: 77.08 -> 79.07Improved
add high-entropy (unreliable) filtering to the full contrastive setup (ablation)Ours · PASCAL VOC 2012 blender, 1/4 (2646) labeledmIoU: 77.57 -> 79.30Improved
add prototypical denoising (ablation)Ours · PASCAL VOC 2012 blender, 1/4 (2646) labeledmIoU: 77.33 -> 77.93Improved
add symmetric cross-entropy for unlabeled images (ablation)Ours · PASCAL VOC 2012 blender, 1/4 (2646) labeledmIoU: 77.33 -> 77.69Improved
add prototypical denoising across partitions (ablation)Ours · PASCAL VOC 2012 blender, 1/4 (2646) labeledmIoU: 79.48 -> 80.21Improved
use reverse-only CE instead of symmetric CE (ablation)Ours · PASCAL VOC 2012 blender, 1/8 (1323) labeledmIoU: 79.35 -> 77.76Hurt
use probability rank thresholds r_l=3, r_h=20 instead of r_l=10, r_h=20 (ablation)Ours · PASCAL VOC 2012 blender, 1/4 (2646) labeledmIoU: 78.94 -> 80.21Improved
use initial unreliable partition 20% instead of 40% (ablation)Ours · PASCAL VOC 2012 blender, 1/4 (2646) labeledmIoU: 76.92 -> 80.21Improved

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