AI Paper Atlas

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

Complementary to Multiple Labels: A Correlation-Aware Correction Approach

Yi Dan Gao, Miao Xu, Min-Ling Zhang

TPAMI 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 9 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 correlation-based correction C of transition matrix (ablation)MLCL · yeast (uniform complementary labels)average precision: .472 -> .718Improved
add correction C (ablation)MLCL · corel5k (uniform complementary labels)average precision: .274 -> .391Improved
add correction C (ablation)MLCL · scene (uniform complementary labels)average precision: .671 -> .699Improved
add correction C (ablation)MLCL · eurlex_dc (biased complementary labels)hamming loss: .088 -> .109Hurt
add MSE regularizer (ablation)MLCL · scene (uniform complementary labels)average precision: .566 -> .699Improved
add MSE regularizer (ablation)MLCL · eurlex_dc (uniform complementary labels)average precision: .426 -> .549Improved
add MSE regularizer (ablation)MLCL · yeast (uniform complementary labels)average precision: .711 -> .718No clear effect
add MSE regularizer (ablation)MLCL · corel5k (uniform complementary labels)average precision: .389 -> .391No clear effect
increase beta from 0.1 to 1 (ablation)MLCL · scene (uniform complementary labels)average precision: .678 -> .699Improved
increase beta from 0.1 to 1 (ablation)MLCL · bookmark (uniform complementary labels)average precision: .565 -> .584Improved
increase beta from 0.1 to 1 (ablation)MLCL · delicious (uniform complementary labels)average precision: .554 -> .572No clear effect
add one relevant label per instance to complementary labelMLCL · sceneaverage precision: .699 -> .860Improved

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