AI Paper Atlas

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

Label Embedding with Partial Heterogeneous Contexts

Yaxin Shi, Donna Xu, Yuangang Pan, Ivor W. Tsang, Shirui Pan

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 8 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 PHCLE instead of the strongest single-context or fusion baselinezero-shot classification embeddings · AWA, ESZSLaverage per-class top-1 accuracy: 63.66 -> 69.11Improved
use PHCLE instead of the strongest baselinezero-shot classification embeddings · AWA, ConSEaverage per-class top-1 accuracy: 58.08 -> 58.43Improved
use PHCLE instead of the strongest baselinezero-shot classification embeddings · AWA, SJEaverage per-class top-1 accuracy: 74.27 -> 77.47Improved
use PHCLE instead of the strongest baselinezero-shot classification embeddings · aPY, ESZSLaverage per-class top-1 accuracy: 52.60 -> 54.61Improved
use PHCLE instead of the strongest baselinezero-shot classification embeddings · aPY, ConSEaverage per-class top-1 accuracy: 52.87 -> 52.87No clear effect
use PHCLE instead of the strongest baselinezero-shot classification embeddings · aPY, SJEaverage per-class top-1 accuracy: 52.18 -> 50.91Hurt
use PHCLE instead of TADW with full context correspondencefull-context label embeddings · AWA, ESZSLaverage per-class top-1 accuracy: 50.18 -> 69.08Improved
use PHCLE instead of TADW with full context correspondencefull-context label embeddings · AWA, ConSEaverage per-class top-1 accuracy: 56.62 -> 56.77Improved
use PHCLE instead of TADW with full context correspondencefull-context label embeddings · AWA, SJEaverage per-class top-1 accuracy: 40.84 -> 53.33Improved
use PHCLE instead of TADW with full context correspondencefull-context label embeddings · aPY, ESZSLaverage per-class top-1 accuracy: 28.13 -> 50.56Improved
use PHCLE instead of TADW with full context correspondencefull-context label embeddings · aPY, ConSEaverage per-class top-1 accuracy: 25.21 -> 53.04Improved
use PHCLE instead of TADW with full context correspondencefull-context label embeddings · aPY, SJEaverage per-class top-1 accuracy: 23.48 -> 42.52Improved

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