SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.17709 · CVPR · 2024

Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection

Hyunwoo Kim, Jinyoung Park, Jinyoung Kim, Jihwan Park, Jongha Kim, Sehyung Kim

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2403.17709.json · badge: /api/ran/2403.17709.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
mlvlab/SpeaQ canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
argsort_desc Ran
ran, honoured the contract we drafted
mlvlab/SpeaQ/evaluation/utils.py
pointer only (licence: NONE) · get_code("7d4002289969a288")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mlvlab/SpeaQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gen_sineembed_for_position Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mlvlab/SpeaQ/modeling/transformer/detr.py
pointer only (licence: NONE) · get_code("0f17ae0853df90a4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mlvlab/SpeaQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

intersect_2d Ran
ran, violated the contract we drafted
mlvlab/SpeaQ/evaluation/utils.py
pointer only (licence: NONE) · get_code("6727d2d8f1d79998")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mlvlab/SpeaQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
argsort_desc 5 other papers
2 dated earlier, 3 later
1903.02728 (2019-03)
Graphical Contrastive Losses for Scene Graph Parsing
2004.00436 (2020-04)
Exploring Long Tail Visual Relationship Recognition with Large Vocabulary
2404.02072 (2024-04)
EGTR: Extracting Graph from Transformer for Scene Graph Generation
and 2 more not named here
intersect_2d 5 other papers
2 dated earlier, 3 later
2004.00436 (2020-04)
Exploring Long Tail Visual Relationship Recognition with Large Vocabulary
2103.16083 (2021-03)
Fully Convolutional Scene Graph Generation
2404.02072 (2024-04)
EGTR: Extracting Graph from Transformer for Scene Graph Generation
and 2 more not named here
gen_sineembed_for_position 3 other papers
2 dated earlier, 1 later
2108.06152 (2021-08)
Conditional DETR for Fast Training Convergence
2307.12239 (2023-07)
Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation
2411.10293 (2024-11)
RETR: Multi-View Radar Detection Transformer for Indoor Perception

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Visual Relationship Detection (VRD) has seen significant advancements with Transformer-based architectures recently. However, we identify two key limitations in a conventional label assignment for training Transformer-based VRD models, which is a process of mapping a ground-truth (GT) to a prediction. Under the conventional assignment, an 'unspecialized' query is trained since a query is expected to detect every relation, which makes it difficult for a query to specialize in specific relations. Furthermore, a query is also insufficiently trained since a GT is assigned only to a single prediction, therefore near-correct or even correct predictions are suppressed by being assigned 'no relation (?)' as a GT. To address these issues, we propose Groupwise Query Specialization and Quality-Aware Multi-Assignment (SpeaQ). Groupwise Query Specialization trains a 'specialized' query by dividing queries and relations into disjoint groups and directing a query in a specific query group solely toward relations in the corresponding relation group. Quality-Aware Multi-Assignment further facilitates the training by assigning a GT to multiple predictions that are significantly close to a GT in terms of a subject, an object, and the relation in between. Experimental results and analyses show that SpeaQ effectively trains 'specialized' queries, which better utilize the capacity of a model, resulting in consistent performance gains with 'zero' additional inference cost across multiple VRD models and benchmarks. Code is available at https://github.com/mlvlab/SpeaQ.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.17709")
get_code_for_paper("2403.17709")
have("2403.17709")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.17709.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.17709.svg)](https://syntology.ai/paper/2403.17709)

Connect an agent — have() is free.