AI Paper Atlas

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

Latent Topic-aware Multi-Label Classification

Jianghong Ma, Yang Liu

ECCV 2020 · 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
use topic-aware TMLC instead of CoECoE · cal500Macro-F1: 0.111 -> 0.240Improved
use topic-aware TMLC instead of CoECoE · corel5kMicro-F1: 0.301 -> 0.312Improved
use topic-aware TMLC instead of CoECoE · yeastExample-F1: 0.598 -> 0.638Improved
use topic-aware TMLC instead of CoECoE · iaprtc12Macro-F1: 0.150 -> 0.135Hurt
use topic-aware TMLC instead of CoECoE · espgameMacro-F1: 0.141 -> 0.086Hurt
use topic-aware TMLC instead of CoECoE · pascal07Micro-F1: 0.454 -> 0.451No clear effect
use topic-aware TMLC instead of CoECoE · mirflickrMacro-F1: 0.005 -> 0.010No clear effect
use TMLC label-specific topic features instead of JFSCJFSC · corel5kMicro-F1: 0.109 -> 0.312Improved
use TMLC label-specific topic features instead of LLSFDLLLSFDL · iaprtc12Micro-F1: 0.096 -> 0.323Improved
set alpha equal to beta in the sample extractionTMLC · corel5kMacro-F1/Micro-F1Improved
set lambda larger than sigma in feature extractionTMLC · corel5kMacro-F1/Micro-F1Improved

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