AI Paper Atlas

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

Zero Shot Learning with the Isoperimetric Loss

AAAI 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 2 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 isoperimetric graph regularization to the linear ZSL baselineZero-IPL · AwA1top-1 accuracy (%): 58.6% to 76.03%Helped
Add isoperimetric graph regularization to the linear ZSL baselineZero-IPL · AwA2top-1 accuracy (%): 58.6% to 73.46%Helped
Add isoperimetric graph regularization to the linear ZSL baselineZero-IPL · CUBtop-1 accuracy (%): 23.8% to 39.45%Helped
Change the k-nearest-neighbor graph parameter by 50% (ablation)Zero-IPL · AwA1top-1 accuracy (%): performance drop of less than 2.6%Hurt
Change the k-nearest-neighbor graph parameter by 50% (ablation)Zero-IPL · AwA2top-1 accuracy (%): performance drop of less than 8.77%Hurt
Change the k-nearest-neighbor graph parameter by 50% (ablation)Zero-IPL · CUBtop-1 accuracy (%): performance drop of less than 2.02%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