AI Paper Atlas

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

Learning Semantic Part-Based Models from Google Images

Davide Modolo, Vittorio Ferrari

TPAMI 2017 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 11 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
add polishing of web part instances (A0 to A1) (ablation)part appearance model · PASCAL-Part valmAP: 12.9 -> 15.7Improved
add viewpoint-specific part location model to A1 (ablation)A1 · PASCAL-Part valmAP: 15.7 -> 18.3Improved
mine more part instances using object-part association and update appearance (A2) (ablation)A1 · PASCAL-Part valmAP: 18.3 -> 22.0Improved
combine A2 with location model L2 (ablation)A2 · PASCAL-Part valmAP: 22.0 -> 23.5Improved
adapt appearance to PASCAL VOC domain (A3) (ablation)A2 + L2 · PASCAL-Part valmAP: 23.5 -> 25.4Improved
adapt location model to VOC domain (L3 instead of L2) (ablation)A3 · PASCAL-Part valmAP: 26.8 -> 27.2Improved
learn from web part images with all stages instead of naive part-name queries (ablation)part detector · PASCAL-Part valmAP: 12.9 to 27.2 APImproved
train viewpoint classifier on Google Images instead of VOC manual annotationsviewpoint classifier · PASCAL VOC valmean AP: 49.3 -> 53.7Improved
add web part models to R-CNN (VOC 2010)R-CNN · PASCAL VOC 2010 valmean AP: 57.4 -> 59.6Improved
add web part models to R-CNN (VOC 2012)R-CNN · PASCAL VOC 2012 valmean AP: 56.5 -> 58.5Improved
add web object images to R-CNN training dataR-CNN · PASCAL VOC 2010 valmean AP: 57.4 -> 56.6Hurt
add web part instances to fully supervised part detectorA_FS1 · PASCAL-Part valmAP: 43.9 -> 41.5Hurt

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