AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Learning Non-Target Knowledge for Few-Shot Semantic Segmentation

Yuanwei Liu, Nian Liu, Qinglong Cao, Xiwen Yao, Junwei Han, Ling Shao

CVPR 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot segmentation · 143 citations (OpenAlex)

This paper tried a common change: Add a contrastive loss

Add prototypical contrastive learning to BGEM + DOEM · PASCAL-5^i 1-shot · mIoU: 63.6 -> 64.2 Improved

What 1,317 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

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
Eliminate BG regions with BGEM (ablation)NTRENet · PASCAL-5^i 1-shotmIoU: 60.0 -> 62.4Improved
Eliminate DO regions with DOEM after BGEM (ablation)NTRENet · PASCAL-5^i 1-shotmIoU: 62.4 -> 63.6Improved
Add prototypical contrastive learning to BGEM + DOEM (ablation)NTRENet · PASCAL-5^i 1-shotmIoU: 63.6 -> 64.2Improved
Eliminate BG regions with BGEM (ablation)NTRENet · PASCAL-5^i 1-shotprecision: 61.9 -> 62.8Improved
Eliminate DO regions with DOEM after BGEM (ablation)NTRENet · PASCAL-5^i 1-shotprecision: 62.8 -> 63.3Improved
Add prototypical contrastive learning to BGEM + DOEM (ablation)NTRENet · PASCAL-5^i 1-shotprecision: 63.3 -> 63.6Improved
Use DO prototypes rather than whole non-target prototypes as PCL negatives (ablation)NTRENet · PASCAL-5^i 1-shotmIoU: 61.8 -> 64.2Improved
Use DO prototypes rather than BG prototypes as PCL negatives (ablation)NTRENet · PASCAL-5^i 1-shotmIoU: 62.6 -> 64.2Improved
Vary BG prototype channel dimension (ablation)NTRENet · PASCAL-5^i 1-shotmIoUMixed
Mine and eliminate non-target regions rather than directly focusing only on target segmentationNTRENet · PASCAL-5^i 1-shotmIoU: 61.8 -> 64.2Improved
Mine and eliminate non-target regions rather than directly focusing only on target segmentationNTRENet · COCO-20^i 1-shotmIoU: 34.6 -> 39.3Improved

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