AI Paper Atlas

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

Learning Invariant Visual Representations for Compositional Zero-Shot Learning

Tian Zhang, Kongming Liang, Ruoyi Du, Xian Sun, Zhanyu Ma, Jun Guo

ECCV 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 45 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 L_cls to L_comp (ablation)L_comp baseline · UT-Zappos50KAUC: 27.8 -> 28.8Mixed
add L_cls to L_comp (ablation)L_comp baseline · Clothing16KAUC: 82.9 -> 84.8Improved
add L_rep to L_cls+L_comp (ablation)L_cls+L_comp · UT-Zappos50KAUC: 28.8 -> 29.8Improved
add L_rep to L_cls+L_comp (ablation)L_cls+L_comp · Clothing16KAUC: 84.8 -> 85.3Improved
add L_grad to L_cls+L_comp (ablation)L_cls+L_comp · UT-Zappos50KAUC: 28.8 -> 30.0Improved
add L_grad to L_cls+L_comp (ablation)L_cls+L_comp · Clothing16KAUC: 84.8 -> 86.3Improved
add L_grad to L_cls+L_comp+L_rep (ablation)full method · UT-Zappos50KAUC: 29.8 -> 30.6Improved
add L_rep to L_cls+L_comp+L_grad (ablation)full method · Clothing16KAUC: 86.3 -> 87.0Improved
add L_rep to L_cls+L_comp (ablation)L_cls+L_comp · UT-Zappos50KSeen accuracy: 57.0 -> 55.9Hurt
use Euclidean instead of cosine gradient distance (ablation)L_grad · UT-Zappos50KAUC: 28.6 -> 30.6Improved
use Euclidean instead of cosine gradient distance (ablation)L_grad · Clothing16KAUC: 85.9 -> 87.0Improved
increase discard ratio alpha from 1/6 to 1/2 (ablation)channel mask · UT-Zappos50KAUC: 30.6 -> 28.5Hurt

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