AI Paper Atlas

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

Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks

Federico Baldassarre, Kevin Smith, Josephine Sullivan, Hossein Azizpour

ECCV 2020 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 22 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 human-object graph prior instead of uniform fully-connected graph (ablation)explanation-based detector · HICO-DET Full (600)mAP: 24.25 -> 28.04Improved
replace uniform prior with frequency-based relationship prior (ablation)explanation-based detector · VRD predicate detection (GT objects)recall@50: 27.3 -> 43.0Improved
replace uniform prior with frequency-based relationship prior (ablation)explanation-based detector · VRD relationship detection (R-CNN objects)recall@50: 5.3 -> 10.6Improved
replace uniform prior with frequency-based relationship prior (ablation)explanation-based detector · VRD zero-shot predicate detection (GT objects)recall@50: 13.7 -> 13.5No clear effect
give prior access to a few zero-shot triplets (ablation)explanation-based detector · VRD zero-shot predicate detection (GT objects)recall@50: 13.7 -> 20.5Improved
replace uniform prior with frequency prior (ablation)explanation-based detector · UnRel relationship detection (R-CNN objects)mAP: 14.9 -> 15.1No clear effect
use image-level predicate labels only versus fully supervised triplet labelsexplanation-based detector · HICO-DET Full (600)mAP: 19.40 -> 28.04Improved
weak predicate-only supervision versus weak triplet supervision (Peyre)explanation-based detector · VRD predicate detection (GT objects)recall@100: 46.8 -> 57.4Improved
weak predicate-only supervision versus weak triplet supervision (Peyre)explanation-based detector · VRD relationship detection (R-CNN objects)recall@50: 14.1 -> 10.6Hurt
change relevance computation (gradient x input, max(.,0), L1 or L2 norm) (ablation)explanation step · validation splitrelationship detectionNo clear effect
use mean pooling instead of max pooling in the graph aggregation (ablation)predicate classifier · VRDrecall@50 and recall@100Mixed
increase number N of explained predicates beyond 10-20 (ablation)explanation step · VRDrecall@50 and recall@100No clear effect

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