atlas

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

Zero-Shot Recognition via Direct Classifier Learning with Transferred Samples and Pseudo Labels

AAAI 2017 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 19 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
Use one-step direct classifiers with pseudo labels instead of two-step attribute-space ZSR (inductive)Zero-shot recognition · CIFAR10accuracy (%): 88.30 -> 89.52Helped
Inductive proposed vs best two-step baseline on aPYOurs-Inductive · aPascal-aYahooaccuracy (%): 46.23 -> 43.59Hurt
Add unlabeled target samples with iterative label refinement (transductive) (ablation)Ours · aPYaccuracy (%): 43.59 -> 50.84Helped
Add unlabeled target samples with iterative refinement (ablation)Ours · AwAaccuracy (%): 79.07 -> 81.90Helped
Increase number of selected source samples ms (ablation)Ours · CIFAR10accuracyHelped
Increase ms beyond 400 to 600 (ablation)Ours · aPY and SUNaccuracyHurt
Increase noise parameter mu of robust SVM (ablation)Ours · four datasetsaccuracyMixed

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