AI Paper Atlas

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

Generalized Zero-Shot Learning with Deep Calibration Network

Shichen Liu, Mingsheng Long, Jianmin Wang, Michael I Jordan

NeurIPS 2018 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 168 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
DCN vs best baseline ALEGZSL · AwA GZSL (PS)harmonic mean H: 27.5 -> 39.1Improved
DCN vs ZSKLGZSL · aPY GZSL (PS)harmonic mean H: 18.5 -> 23.9Improved
add entropy (uncertainty) calibration on target classes (ablation)DCN · AwA GZSL (PS)harmonic mean H: 28.6 -> 39.1Improved
add entropy calibration (ablation)DCN · SUN GZSL (PS)harmonic mean H: 29.1 -> 30.2Improved
add temperature calibration (ablation)DCN w/o E · CUB GZSL (PS)harmonic mean H: 35.2 -> 37.2Improved
add temperature calibration (ablation)DCN w/o E · AwA GZSL (PS)harmonic mean H: 28.6 -> 28.6No clear effect
add temperature calibration (ablation)DCN · Avg ZSL (PS)top-1 accuracy: 54.4 -> 56.7Improved

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