AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

LaSO: Label-Set Operations Networks for Multi-Label Few-Shot Learning

Amit Alfassy, Leonid Karlinsky, Amit Aides, Joseph Shtok, Sivan Harary, Rogerio Feris, Raja Giryes, Alex M. Bronstein

CVPR 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 124 citations (OpenAlex)

This paper tried a common change: Add a reconstruction / auxiliary loss

Add symmetry reconstruction loss · MS-COCO 64 seen categories · mAP: 0.72 -> 0.76 Improved

What 987 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
Use LaSO union augmentation instead of the strongest listed baseline, mixUPMS-COCO 16 unseen categories, 1-shot classifier · MS-COCO 16 unseen categories, 1-shotmAP: 40.2 -> 45.3Improved
Use LaSO union augmentation instead of the strongest listed baseline, mixUPMS-COCO 16 unseen categories, 5-shot classifier · MS-COCO 16 unseen categories, 5-shotmAP: 54.0 -> 58.1Improved
Use a learned LaSO operator instead of the analytic feature-wise expressionMS-COCO label-set subtraction · MS-COCOmAP: 29.0 -> 43.0Improved
Use a learned LaSO operator instead of the analytic feature-wise expressionCelebA label-set subtraction · CelebAmAP: 37.0 -> 69.0Improved
Use a learned operator instead of min(FX, FY)MS-COCO label-set intersection · MS-COCOmAP: 74.7 -> 77.0Improved
Use a learned operator instead of min(FX, FY)CelebA label-set intersection · CelebAmAP: 52.0 -> 48.0Hurt
Use a learned operator instead of max(FX, FY)MS-COCO label-set union · MS-COCOmAP: 76.5 -> 81.0Improved
Use a learned operator instead of max(FX, FY)CelebA label-set union · CelebAmAP: 47.0 -> 75Improved
Add symmetry reconstruction loss (ablation)LaSO intersection · MS-COCO 64 seen categoriesmAP: 0.72 -> 0.76Improved
Add mode-collapse reconstruction loss after adding symmetry loss (ablation)LaSO subtraction · MS-COCO 64 seen categoriesmAP: 0.39 -> 0.43Improved
Add both reconstruction losses (ablation)LaSO operators · MS-COCO 64 seen categoriesmAP: 3% − 9%Improved
Add mode-collapse reconstruction loss during LaSO training (ablation)LaSO retrieval outputs · MS-COCO seen and unseen categoriesretrieved-sample diversity: 5%; 9%Improved

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