atlas

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

Dual-View Ranking with Hardness Assessment for Zero-Shot Learning

AAAI 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 12 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 hardness assessment (sigmoid triplet weighting) (ablation)DARK · average over AwA2/aPY/SUN/CUBZSL ACC: 60.73 -> 61.13Helped
add hardness assessment (sigmoid triplet weighting) (ablation)DARK · average over AwA2/aPY/SUN/CUBGZSL H: 32.85 -> 34.93Helped
add label-view image ranking (dual-view ranking) (ablation)image-view ranking baseline (ALE as reference) · AwA2, aPY, SUN, CUBACC and HHelped
add hardness assessment to image-view ranking (ablation)ALE-like image-view ranking · AwA2, aPY, SUN, CUBACC and HHelped
replace ALE with DARK (dual-view ranking plus hardness)ZSL ranking loss · average over four datasetsZSL ACC: 53.80 -> 61.13Helped
replace ZKL with DARKZSL ranking loss · AwA2ZSL ACC: 70.5 -> 68.9Hurt

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