AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

IGNORE: Information Gap-based False Negative Loss Rejection for Single Positive Multi-Label Learning

Gyeong Ryeol Song, Noo-ri Kim, Jin-Seop Lee, Jee-Hyong Lee

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 4 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 IGNORE rejection, SPBC and consistency regularization to AN loss (ablation)Q2L · PASCAL VOC 2012mAP: 87.9 -> 90.1Improved
add logit average threshold to IGNORE+SPBC+consistency (ablation)Q2L · NUSWIDEmAP: 52.0 -> 52.8Improved
add logit average threshold to IGNORE+SPBC+consistency (ablation)Q2L · CUBmAP: 22.8 -> 23.4Improved
add logit average threshold (ablation)Q2L · PASCAL VOC 2012mAP: 90.0 -> 90.1No clear effect
apply consistency regularization alone without IGNORE and SPBC (ablation)Q2L · NUSWIDE and CUBmAP: NUSWIDE 49.2 -> 47.5; CUB 19.7 -> 11.1Hurt
apply consistency regularization alone (ablation)Q2L · COCOmAP: 73.5 -> 73.6No clear effect
add IGNORE and SPBC on top of consistency regularization (ablation)Q2L · COCOmAP: 73.6 -> 76.2Improved
add logit average threshold to gap-only rejection (ablation)IGNORE · PASCAL VOC 2012rejection ratio FN/TNImproved
vary CAM threshold used to build masked image (ablation)IGNORE · SPML datasetstest mAPNo clear effect
use IGNORE versus best prior method with ResNet-50ResNet-50 on COCO · MS COCO (SPML)mAP: 72.89 -> 72.00Hurt

Later papers that compared with this method

1 later accepted paper reports Ignore as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

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