AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Weakly-Supervised Learning of Visual Relations

Julia Peyre, Josef Sivic, Ivan Laptev, Cordelia Schmid

ICCV 2017 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 193 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 spatial features to appearance features (ablation)Ours (full sup.) · VRD predicate detection (All)recall@50: 46.3 -> 50.4Improved
add appearance features to spatial features (ablation)Ours (full sup.) · VRD predicate detection (All)recall@50: 42.2 -> 50.4Improved
add spatial features to appearance features (ablation)Ours (full sup.) · VRD predicate detection (Unseen)recall@50: 16.1 -> 23.6Improved
add language scores of Lu et al.Ours [S+A] (full sup.) · VRD predicate detection (All vs Unseen)recall@50: 50.4 -> 52.6 (All); 23.6 -> 21.6 (Unseen)Mixed
switch from full to weak image-level supervisionOurs [S+A] · VRD predicate detection (All)recall@50: 50.4 -> 46.8Hurt
switch from full to weak image-level supervisionOurs [S+A] · VRD predicate detection (Unseen)recall@50: 23.6 -> 19.0Hurt
infer which object pairs are in relation (discriminative clustering) instead of picking a random pair (ablation)Ours [S+A] weak sup. · VRD relationship detection (Unseen)recall@50: 5.6 -> 6.7Improved
infer which object pairs are in relation instead of picking a random pair, with ~5x more candidate pairs (ablation)Ours [S+A] weak sup. · VRD harder candidate setup, phrase detectionrecall@50: 15.3 -> 17.9Improved
infer which object pairs are in relation instead of picking a random pair, with ~5x more candidate pairs (ablation)Ours [S+A] weak sup. · VRD harder candidate setup, relationship detectionrecall@50: 10.1 -> 12.0Improved
infer object pairs instead of picking a random pair (ablation)Ours [S+A] weak sup. · UnRel retrieval (with GT boxes)mAP: 55.0 -> 58.5Improved
use spatial plus appearance visual representation instead of union-box appearance classifierOurs [S+A] full sup. · UnRel retrieval (with GT boxes)mAP: 50.6 -> 62.6Improved
use spatial plus appearance visual representation instead of union-box appearance classifierOurs [S+A] full sup. · Visual Genome relationship recognitiontop-1 accuracy: 8.7 -> 46.5Improved

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