AI Paper Atlas

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

A causal view of compositional zero-shot recognition

Yuval Atzmon, Felix Kreuk, Uri Shalit, Gal Chechik

NeurIPS 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 69 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
model stable attribute and object core features and infer pairs by the conditional image likelihoodCausal · AO-CLEVr 5:5 splitUnseen accuracy: 26% to 47%Improved
model stable attribute and object core features and infer pairs by the conditional image likelihoodCausal · AO-CLEVr 5:5 splitSeen accuracy: 86% to 84%Hurt
add conditional-independence regularization to VisProdVisProd · AO-CLEVr 5:5 splitUnseen accuracy: 19% to 38%Improved
add conditional-independence regularization to VisProdVisProd · AO-CLEVr 5:5 splitSeen accuracy: 85% to 82%Hurt
add the independence loss (ablation)Causal · Zappos testUnseen accuracy: 22.5 ± 2.0 -> 26.6 ± 1.6Improved
add the independence loss (ablation)Causal · Zappos testSeen accuracy: 45.5 ± 3.7 -> 39.7 ± 2.2Hurt
add the independence loss (ablation)Causal · Zappos testHarmonic: 29.4 ± 1.5 -> 31.8 ± 1.7Improved
use non-alternating rather than alternating optimization (ablation)AO-CLEVr Causal · AO-CLEVroverall resultsMixed
remove frequency weighting from the attribute and object reconstruction losses (ablation)AO-CLEVr Causal · AO-CLEVrHarmonic: 68.8% to 67.6%Hurt
remove frequency weighting from the attribute and object reconstruction losses (ablation)AO-CLEVr Causal · AO-CLEVrUnseen accuracy: 57.5% to 56.2%Hurt

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