AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Fine-Grained Image Classification by Exploring Bipartite-Graph Labels

Feng Zhou, Yuanqing Lin

CVPR 2016 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 138 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 BGL modeling of fine-grained classes with type and model coarse labelsGoogLeNet on Car-333 · Car-333 test, w/o. BBoxtop-1 accuracy: 79.8% -> 86.4%Improved
Use model coarse labels instead of type coarse labels (ablation)BGL on Car-333 · Car-333classification accuracyImproved
Add type labels on top of model labels (ablation)BGL on Car-333 · Car-333classification accuracyImproved
Add BGL with attribute labelsGoogLeNet on CUB-200-2011 · CUB-200-2011 test, w/o. BBoxclassification accuracyImproved
Add BGL with dish and ingredient labels together rather than using only one label type (ablation)BGL on Food-975 · Food-975 controlled and wild settingsclassification accuracyImproved
Add BGL to the GoogLeNet baselineGoogLeNet on Food-975 · Food-975 wildclassification accuracy: 6 ~ 7%Improved
Add BGL to the CNN classifierCNNs on Stanford cars · Stanford carsclassification accuracyImproved

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