AI Paper Atlas

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

Deep Streaming Label Learning

Zhen Wang, Liu Liu, Dacheng Tao

ICML 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 18 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 streaming feature distillation (KD) to the plain deep network (ablation)DSLL new-label classifier · MirFlickr, 9 new labelsaverage precision: 0.3824 to 0.4018Improved
replace cross-entropy with label correlation-aware loss (LC) in streaming label mapping (ablation)streaming label mapping · MirFlickr, 9 new labelsaverage precision: 0.4113 to 0.4182 (slight)Improved
add transformation layer St after streaming label mapping (ablation)LC label mapping · MirFlickr, 9 new labelsaverage precision: 0.4182 to 0.4287Improved
use both hard and soft past labels as mapping input vs hard only (ablation)streaming label mapping · MirFlickr, 9 new labelsaverage precision: Lhard_soft 0.4592 vs Lhard 0.4159 but Lsoft 0.4427 is higher than LhardMixed
full DSLL (KD + LC-St + hard/soft mapping) vs plain baseline (ablation)DSLL · MirFlickr, 9 new labelsaverage precision: 0.3824 to 0.4925Improved
full DSLL vs plain baseline on coverage (ablation)DSLL · MirFlickr, 9 new labelscoverage: 0.2415 to 0.2153 (lower is better)Improved
full DSLL vs strongest baseline (C2AE)DSLL · Wiki10 and MirFlickr, micro-AUC and ranking lossmicro-AUC / ranking loss: Wiki10 1k micro-AUC 0.8406 vs 0.8274; ranking loss 0.0421 vs 0.0483Improved
full DSLL vs SLL/SML and C2AE on EURlex and DeliciousDSLL · EURlex 1000 new labels micro-AUCmicro-AUC: DSLL 0.9106 vs SLL 0.9115Mixed

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