AI Paper Atlas

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

Proposal Flow: Semantic Correspondences from Object Proposals

Bumsub Ham, Minsu Cho, Cordelia Schmid, Jean Ponce

TPAMI 2017 · Detection and segmentation › Open-set and few-shot detection · approach: Visual relationship and scene graph detection · 117 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
use object proposals (SS) instead of sliding windows within proposal flow with LOM (ablation)LOM · PF-WILLOWPCK (alpha=0.1): 0.42 -> 0.56Improved
use SS instead of SW proposals on Caltech-101 (ablation)LOM · Caltech-101IoU: 0.47 -> 0.50Improved
add local offset regularization (LOM) over PHM when background clutter is heavy (ablation)PHM · PF-PASCAL qualitative paircorrect matches at IoU 0.5: 16, 5, and 38 for NAM, PHM, and LOMImproved
use LOM instead of NAM (ablation)proposal flow with SS · PF-PASCALPCK (alpha=0.1): 0.36 -> 0.45Improved
use LOM instead of PHM (ablation)proposal flow with SS · PF-PASCALPCK (alpha=0.1): 0.42 -> 0.45Improved
use HOG descriptor instead of CNN features (AlexNet layers, SIAM) (ablation)LOM with RP · PF-PASCALAuC of PCRImproved
use RP proposals instead of other proposals (ablation)LOM w/ HOG · PF-PASCALmatching precisionImproved
increase number of object proposals (except MCG) (ablation)proposal flow · PF-PASCAL and PF-WILLOWAuC of PCR: saturate around 1000 proposalsImproved
increase number of MCG proposals (ablation)LOM w/ MCG · PF-PASCAL and PF-WILLOWAuC of PCRHurt
remove background clutter (wine without clutter vs with clutter)LOM · PF-WILLOWAuC of PCR: 0.30 -> 0.69Improved
add SS proposal flow vs FlowWeb multi-image refinement on PASCAL partsLOM · PASCAL partsPCK: 0.17 vs 0.26Hurt
LOM vs Taniai et al. on FG3DCarLOM · Taniai's benchmark FG3DCarmatching accuracy: 0.79 vs 0.83Hurt

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