AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning

Shiming Chen, Guosen Xie, Yang Liu, Qinmu Peng, Baigui Sun, Hao Li, Xinge You, Ling Shao

NeurIPS 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 85 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 structure adaptation (SAD) constraints (ablation)HSVA · AWA1 GZSLharmonic mean H: 62.3 -> 66.8Improved
add structure adaptation (SAD) constraints (ablation)HSVA · CUB GZSLharmonic mean H: 53.2 -> 55.3Improved
add structure adaptation (SAD) constraints (ablation)HSVA · SUN GZSLharmonic mean H: 42.6 -> 43.3Improved
add distribution adaptation (Wasserstein + iCORAL) constraints (ablation)HSVA · AWA1 GZSLharmonic mean H: 43.4 -> 66.8Improved
add distribution adaptation (Wasserstein + iCORAL) constraints (ablation)HSVA · CUB GZSLharmonic mean H: 47.9 -> 55.3Improved
add distribution adaptation (Wasserstein + iCORAL) constraints (ablation)HSVA · SUN GZSLharmonic mean H: 38.6 -> 43.3Improved
add inverse CORAL loss (ablation)HSVA · AWA1 GZSLharmonic mean H: 62.4 -> 66.8Improved
add inverse CORAL loss (ablation)HSVA · AWA2 GZSLharmonic mean H: 63.3 -> 66.3Improved
add inverse CORAL loss (ablation)HSVA · CUB GZSLharmonic mean H: 53.9 -> 55.3Improved
add inverse CORAL loss (ablation)HSVA · SUN GZSLharmonic mean H: 41.8 -> 43.3Improved
add structure adaptation (SAD) constraints (ablation)HSVA · AWA2 GZSLharmonic mean H: 63.5 -> 66.3Improved

Later papers that compared with this method

3 later accepted papers report HSVA as a baseline in their results tables; 1 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