AI Paper Atlas

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

From Zero-Shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesis

Yang Long, Li Liu, Ling Shao, Fumin Shen, Guiguang Ding, Jungong Han

CVPR 2017 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 150 citations (OpenAlex)

Check 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 diffusion regularization to graph regularization (ablation)UVDS · CUB, SUN, and aPY unseen, sample-based SVMaccuracy: 38.58 -> 45.72; 80.00 -> 86.50; 25.59 -> 53.21Improved
Add graph regularization to diffusion regularization (ablation)UVDS · CUB, SUN, and aPY unseen, sample-based SVMaccuracy: 42.24 -> 45.72; 84.00 -> 86.50; 24.22 -> 53.21Improved
Add graph and diffusion regularization to direct linear regression (ablation)UVDS · CUB, SUN, and aPY unseen, sample-based SVMaccuracy: 26.57 -> 45.72; 77.00 -> 86.50; 15.96 -> 53.21Improved
Use SVM instead of nearest-neighbor classification on synthesized image-level featuresUVDS · CUB, SUN, and aPYaccuracyMixed
Use mean synthesized features rather than averaged class-level attributes to form prototypesUVDS · CUB, SUN, and aPY prototype-based classificationaccuracyNo clear effect

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