AI Paper Atlas

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

Classifier and Exemplar Synthesis for Zero-Shot Learning

Soravit Changpinyo, Wei‐Lun Chao, Boqing Gong, Fei Sha

IJCV 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 61 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 predicted exemplars as semantic representations (EXEM) instead of given onesSynC struct · ImageNet (All)ZSL per-class accuracy: 0.99 -> 1.29Improved
apply EXEM exemplar prediction to base ZSL methodsSynC, ConSE, ESZSL · small datasetsZSL accuracy: relatively 2.1-13.3%, 11.4-32.7%, and 1.6-12.0%Improved
use standardized Euclidean distance (1NNs) instead of Euclidean (1NN)EXEM nearest neighbor · CUB (new split)ZSL per-class accuracy: 54.2 -> 58.0Improved
use standardized Euclidean distance (1NNs) instead of Euclidean (1NN)EXEM nearest neighbor · SUN (new split)ZSL per-class accuracy: 63.0 -> 62.9No clear effect
use standardized Euclidean distance (1NNs) instead of Euclidean (1NN)EXEM nearest neighbor · ImageNet (All)ZSL per-class accuracy: 1.26 -> 1.29Improved
regularize the bases v_r instead of w_c (ablation)SynC o-vs-o (GoogLeNet) · AwAZSL accuracy: 69.7% -> 71.7%Improved
regularize the bases v_r instead of w_c (ablation)SynC o-vs-o (GoogLeNet) · CUBZSL accuracy: 53.4% -> 56.4%Improved
regularize the bases v_r instead of w_c (ablation)SynC o-vs-o (GoogLeNet) · SUNZSL accuracy: 62.8% -> 67.5%Improved
learn phantom class semantic representations (ablation)SynC o-vs-o (GoogLeNet) · AwAZSL accuracy: 69.7% -> 71.1%Improved
learn phantom class semantic representations (ablation)SynC o-vs-o (GoogLeNet) · CUBZSL accuracy: 53.4% -> 54.2%Improved
learn phantom class semantic representations (ablation)SynC o-vs-o (GoogLeNet) · SUNZSL accuracy: 62.8% -> 63.3%Improved
reduce the number of seen classes from 645 to 72 (ablation)EXEM (1NN) · SUN (new split)ZSL accuracy: absolute 14.4% dropHurt

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