AI Paper Atlas

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

Semantic Contrastive Embedding for Generalized Zero-Shot Learning

Zongyan Han, Zhenyong Fu, Shuo Chen, Jian Kang Yang

IJCV 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 33 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 semantic embedding to the generator and classify in a new embedding space (hybrid) (ablation)Gen · CUB (GZSL)harmonic mean H (%): 56.6 -> 63.1Improved
simply combine generation with semantic embedding and classify in semantic space (ablation)Gen · CUB (GZSL)harmonic mean H (%): 56.6 -> 55.5Hurt
use new embedding space instead of semantic space (ablation)Gen+SE · CUB (GZSL)harmonic mean H (%): 55.5 -> 63.1Improved
replace semantic embedding with contrastive embedding in the embedding space (ablation)Gen+SE · CUB (GZSL)harmonic mean H (%): 63.1 -> 65.3Improved
replace semantic embedding with contrastive embedding in the embedding space (ablation)Gen+SE · AWA1 (GZSL)harmonic mean H (%): 66.9 -> 69.1Improved
replace semantic embedding with contrastive embedding in semantic space (ablation)Gen+SE (basic) · CUB (GZSL)harmonic mean H (%): 55.5 -> 64.3Improved
add class-level loss to instance-level contrastive loss (ablation)CE-GZSL · CUB (GZSL)harmonic mean H (%): 62.4 -> 65.3Improved
add instance-level loss to class-level contrastive loss (ablation)CE-GZSL · CUB (GZSL)harmonic mean H (%): 63.0 -> 65.3Improved
add class-level loss to instance-level contrastive loss (ablation)CE-GZSL · AWA2 (GZSL)harmonic mean H (%): 68.1 -> 70.0Improved
increase embedding dimension from 256 to 2,048 (ablation)CE-GZSL · AWA1 (GZSL)harmonic mean H (%): 53.3 -> 69.0Improved
increase embedding dimension from 2,048 to 4,096 (ablation)CE-GZSL · CUB (GZSL)harmonic mean H (%): 65.3 -> 65.2No clear effect
use large random batch of 4,096 instead of 1 positive and 50 negatives (ablation)CE-GZSL · AWA1 (GZSL)harmonic mean H (%): 64.9 -> 69.1Improved

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