AI Paper Atlas

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

Vocabulary-Informed Zero-Shot and Open-Set Learning

Yanwei Fu, Xiaomei Wang, Hanze Dong, Yu–Gang Jiang, Meng Wang, Xiangyang Xue, Leonid Sigal

TPAMI 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 23 citations (OpenAlex)

Read the paperCheck 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
learn constraints from the open vocabulary instead of known classes only (ablation)WMM-Voc · AwA zero-shotaccuracy (%): 84.51 -> 90.79Improved
learn constraints from the open vocabulary instead of known classes only (ablation)Deep WMM-Voc · AwA zero-shotaccuracy (%): 83.85 -> 90.65Improved
add density weighting (WMM-Voc over MM-Voc) (ablation)MM-Voc · AwA zero-shot, 200 instances, 1000-dimtop-1 accuracy (%): 83.84 -> 89.09Improved
add density weighting (WMM-Voc over MM-Voc) (ablation)MM-Voc · AwA G-ZSL, 1000-dimtop-1 accuracy (%): 8.54 -> 27.98Improved
add density weighting (WMM-Voc over MM-Voc) (ablation)MM-Voc · AwA open-setfalse positive rate: 0.12 -> 0.05Improved
fine-tune CNN features (Deep WMM-Voc over WMM-Voc) (ablation)WMM-Voc · AwA zero-shot, 100-dimtop-1 accuracy (%): 82.78 -> 84.87Improved
fine-tune CNN features (Deep WMM-Voc over WMM-Voc) (ablation)WMM-Voc · AwA zero-shot, 1000-dimtop-1 accuracy (%): 89.09 -> 88.07Hurt
add density weighting (WMM-Voc over MM-Voc) (ablation)MM-Voc · ImageNet supervisedtop-1 accuracy (%): 37.1 -> 35.95Hurt
fine-tune features (Deep WMM-Voc over WMM-Voc) (ablation)WMM-Voc · ImageNet supervisedtop-1 accuracy (%): 35.95 -> 38.92Improved
use vocabulary-informed learning instead of ESZSLESZSL · AwA G-ZSL, 1000-dimtop-1 accuracy (%): 0 -> 34.77Improved
add vocabulary constraints with more training instancesVoc methods · AwA supervisedaccuracyMixed
use hybrid SGD/L-BFGS solver instead of L-BFGSVoc · large datasetstraining time: 20~50%Improved

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