AI Paper Atlas

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

Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features

Xu Yang, Hanwang Zhang, Jianfei Cai

ECCV 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Visual relationship and scene graph detection · 69 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 OA conv-layers (no pre-training) (ablation)Base relationship model · VRD supervisedRecall@100: 39.25 -> 43.29Improved
add OA conv-layers (no pre-training) (ablation)Base relationship model · VG supervisedRecall@100: 52.61 -> 58.53Improved
add Shuffle-Then-Assemble pre-training to OA layers (ablation)Base+OA · VRD supervisedRecall@100: 43.29 -> 48.03Improved
add Shuffle-Then-Assemble pre-training to OA layers (ablation)Base+OA · VG supervisedRecall@100: 58.53 -> 62.94Improved
add Shuffle-Then-Assemble pre-training to OA layers (ablation)Base+OA · VRD weakly supervisedRecall@100: 31.47 -> 35.89Improved
add Shuffle-Then-Assemble pre-training to OA layers (ablation)Base+OA · VG weakly supervisedRecall@100: 47.72 -> 51.92Improved
add Shuffle-Then-Assemble pre-training to OA layers (ablation)Base+OA · VRD zero-shotRecall@100: 16.53 -> 20.57Improved
add Shuffle-Then-Assemble pre-training to OA layers (ablation)Base+OA · VG zero-shotRecall@100: 13.09 -> 18.90Improved
fine-tune pre-trained OA layers instead of freezing them (ablation)STA · VRD supervisedRecall@100: 44.30 -> 48.03Improved
freeze pre-trained OA layers versus training OA layers from scratch (ablation)STA w/o FT vs Base+OA · VRD supervisedRecall@100: 43.29 -> 44.30No clear effect
use residual structure in the transformation network (ablation)STA · VRD supervisedRecall@100: 46.83 -> 48.03Improved
use residual structure in the transformation network (ablation)STA · VG supervisedRecall@100: 62.32 -> 62.94Improved

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