AI Paper Atlas

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

Non-Generative Generalized Zero-Shot Learning via Task-Correlated Disentanglement and Controllable Samples Synthesis

Yaogong Feng, Xiaowen Huang, Pengbo Yang, Jian Yu, Jitao Sang

CVPR 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 62 citations (OpenAlex)

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 task-correlated feature disentanglement (ablation)TDCSS · AWA2 GZSLH: 61.7 -> 66.1Improved
add edge-pseudo samples (ablation)TDCSS · AWA2 GZSLH: 55.0 -> 66.1Improved
add center-pseudo samples (ablation)TDCSS · AWA2 GZSLH: 48.4 -> 66.1Improved
use TDCSS instead of f-VAEGAN-D2GZSL · AWA1H: 63.5 -> 60.9Hurt
use TDCSS instead of AREN+CSGZSL · CUBH: 66.0 -> 51.9Hurt
use TDCSS instead of SDGZSLFSZU · AWA2, all dataH: 68.6 -> 66.1Hurt
use TDCSS instead of SDGZSLFSZU · CUB, all dataH: 63.2 -> 51.9Hurt
reduce seen-class samples to 2TDCSS · AWA2 FSZUH: 66.1 -> 48.4Hurt
reduce seen-class samples to 2TDCSS · CUB FSZUH: 51.9 -> 36.2Hurt

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