AI Paper Atlas

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

Unified Visual Relationship Detection with Vision and Language Models

Long Zhao, Liangzhe Yuan, Boqing Gong, Yin Cui, Florian Schroff, Ming-Hsuan Yang, Hartwig Adam, Ting Liu

ICCV 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary 3D and world perception · 21 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 cascade two-stage training instead of one-stage end-to-end (ablation)UniVRD · HICO-DETmAP: -5.05 mAP when using one-stageImproved
add Objects365, COCO and VG object detection data (ablation)UniVRD · HICO-DETmAP: -3.96 / -2.67 / -3.16 mAP when removedImproved
add mosaics augmentation (ablation)UniVRD · HICO-DETmAP: -1.76 when removedImproved
use per-class PNMS instead of vanilla or none (ablation)UniVRD · HICO-DETmAP: -2.01 no PNMS, -1.24 vanilla PNMSImproved
freeze object detector and text encoder in the second stage (ablation)UniVRD · HICO-DETmAP: -1.03 (fine-tune detector), -0.92 (fine-tune text encoder)Improved
use CLIP prompt templates or prompt ensemble for relationship text queries (ablation)UniVRD · HICO-DETmAP: 0.00 / +0.01No clear effect
train a unified model on HICO-DET, V-COCO and VG instead of dataset-specificUniVRD · V-COCOmAP Scenario 1: +5.21 (ViT-B/32) to +5.39 (ViT-L/14)Improved
train unified model instead of dataset-specific on Visual GenomeUniVRD · Visual GenomemR@50: -0.01 to -0.32 mR@50Hurt
scale backbone from ViT-B/32 to ViT-H/14 (LiT)UniVRD · HICO-DETmAP: 29.38 -> 38.07Improved
adopt UniVRD bottom-up VLM detector vs best prior bottom-up HOI detectorUniVRD · HICO-DETmAP: +14.26 mAPImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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