AI Paper Atlas

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

Visual Relationship Detection Using Part-and-Sum Transformers With Composite Queries

Qi Dong, Zhuowen Tu, Haofu Liao, Yuting Zhang, Vijay Mahadevan, Stefano Soatto

ICCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Visual relationship and scene graph detection · 47 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 tensor-based query instead of vector-based query (ablation)DETR-style vanilla decoder · VRD Relationship Detection k=70recall@50 / recall@100: 19.97 -> 21.89; 23.08 -> 25.89Improved
replace vanilla decoder by part decoder with tensor query (ablation)tensor query · VRD Relationship Detection k=70recall@50 / recall@100: 21.89 -> 25.46; 25.89 -> 29.65Improved
mix part and sum queries into composite query with vanilla decoder (ablation)vanilla decoder · VRD Relationship Detection k=70recall@50 / recall@100: 19.97 -> 20.17; 23.08 -> 24.53Mixed
decode part and sum queries separately with part-sum interaction (PST decoder) (ablation)composite query with vanilla decoder · VRD Relationship Detection k=70recall@50 / recall@100: 20.17 -> 26.48; 24.53 -> 31.83Improved
add factorized self-attention layer (ablation)PST part stream · VRD Relationship Detection k=1recall@50 / recall@100: 22.14 -> 23.57; 26.48 -> 27.63Improved
add factorized self-attention layer (ablation)PST part stream · VRD Relationship Detection k=70recall@50 / recall@100: 25.30 -> 26.48; 29.17 -> 31.83Improved
use Part-Sum summation interaction instead of self-attention interaction (ablation)PST · VRD Relationship Detection k=70recall@50 / recall@100: 23.89 -> 26.48; 28.87 -> 31.83Improved
use part-only inference instead of sum-only inference (ablation)PST · VRD Relationship Detection k=1recall@50 / recall@100: 22.06 -> 23.57; 25.43 -> 27.63Improved
combine part and sum predictions at inference instead of part only (ablation)PST · VRD Relationship Detection k=1recall@50 / recall@100: 23.57 -> 24.34; 27.63 -> 27.01Mixed
use independent-stream decoding for part and sum queries instead of shared-stream (ablation)PST · VRD Relationship Detection k=1recall@50 / recall@100: 20.04 -> 23.57; 23.10 -> 27.63Improved
increase number of vector queries from 500 to 1500 (ablation)vector query decoder · VRD Relationship Detection k=1recall@50 / recall@100: 17.88 -> 18.63; 19.41 -> 21.14No clear effect
increase vector query dimension to 256x3 (ablation)vector query decoder · VRD Relationship Detection k=1recall@50 / recall@100: 17.88 -> 18.65; 19.41 -> 20.94No clear effect

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