atlas

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

Zero-Shot Recognition Using Dual Visual-Semantic Mapping Paths

CVPR 2017 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 151 citations (OpenAlex)

Check 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 two iterations of manifold alignment (ablation)DMaP-I · AwA cZSRaverage accuracy (%): 80.63 -> 90.49Helped
Add two iterations of manifold alignment (ablation)DMaP-I · AwA gZSRaverage accuracy (%): 2.72 -> 17.82Helped
Add two iterations of manifold alignment (ablation)DMaP-I · CUB cZSRaverage accuracy (%): 56.34 -> 67.69Helped
Add two iterations of manifold alignment (ablation)DMaP-I · Dogs cZSRaverage accuracy (%): 30.90 -> 44.59Helped
Add two iterations of manifold alignment (ablation)DMaP-I · ImageNet cZSRtop-1 accuracy (%): 28.30 -> 38.94Helped
Use attributes plus skipgram embeddings instead of skipgram aloneDMaP-I with vgg+goog+res on CUB · CUB cZSRaverage accuracy (%): 27.48 -> 56.34Helped

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