AI Paper Atlas

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

Zero and Few Shot Learning With Semantic Feature Synthesis and Competitive Learning

Jiechao Guan, Zhiwu Lu, Tao Xiang, Aoxue Li, An Zhao, Ji-Rong Wen

TPAMI 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 80 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 feature synthesis (SFSP) to bidirectional projection learning (ablation)BPL · AwA, CUB, SUNZSL accuracy: 3% to 7% improvementImproved
add competitive learning (ablation)BPL · AwA, CUB, SUNZSL accuracy: 1-3% gainsImproved
use bidirectional instead of single-direction projection learning (ablation)BPL0 · AwA, CUB, SUNZSL accuracyImproved
replace no-ambiguity-handling with competitive learning (ablation)BPL · AwA (pure ZSL)accuracy: 62.9 -> 74.1Improved
replace minimum entropy with competitive learning (ablation)BPL · AwA (pure ZSL)accuracy: 67.1 -> 74.1Improved
replace minimum entropy with competitive learning (ablation)BPL · CUB (pure ZSL)accuracy: 59.0 -> 61.9Improved
replace minimum entropy with competitive learning (ablation)BPL · SUN (pure ZSL)accuracy: 59.6 -> 63.2Improved
use few-shot real samples (SFSP1) rather than base class samples (SFSP2) for synthesis (ablation)BPL · ImNet FSL K=1hit@1: 22.7 -> 22.8No clear effect
use SFSP1 instead of SFSP2 (ablation)BPL · ImNet FSLtraining runtime (min): 2.3 -> 1.2Improved
add base class knowledge transfer via joint projection learning (ablation)BPL (novel) · ImNet FSLhit accuracyImproved
use stronger WRN features instead of Simple CNNOurs · mini-ImageNet 5-way 5-shotaccuracy: 65.28 -> 75.62Improved
use proposed model instead of PPABPL · mini-ImageNet 5-way 5-shot (WRN)accuracy: 73.74 -> 75.62Improved

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