SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.11949 · 2020

Unbiased Scene Graph Generation from Biased Training

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures 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/2002.11949.json · badge: /api/ran/2002.11949.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
KaihuaTang/Scene-Graph-Benchmark.pytorch canonical (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
ihaeyong/unbiased-sgg reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
coldmanck/recovering-unbiased-scene-graphs reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
build_roi_relation_head Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from Wayfear/Coacher
pointer only; the stored copy get_code serves, from Wayfear/Coacher, is pointer only (licence: NOASSERTION) · get_code("fbc88f9f38569eea")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

build_roi_relation_head Ran
ran; our contract draft was wrong, not the code
ihaeyong/unbiased-sgg/maskrcnn_benchmark/modeling/roi_heads/relation_head/relation_head.py
pointer only (licence: NOASSERTION) · get_code("32a2dca6019370be")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ihaeyong/unbiased-sgg (NOASSERTION). 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.

entropy_loss Ran
ran; our contract draft was wrong, not the code
KaihuaTang/Scene-Graph-Benchmark.pytorch/maskrcnn_benchmark/layers/entropy_loss.py
pointer only (licence: MIT); the stored copy get_code serves, from KanghoonYoon/torch-rasgg, is pointer only (licence: NONE) · get_code("2d943c0c96e61f16")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, KaihuaTang/Scene-Graph-Benchmark.pytorch, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

get_center_delta Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
coldmanck/recovering-unbiased-scene-graphs/tools/relation_train_net.py
pointer only (licence: NONE) · get_code("6811cd526ab3e1a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, coldmanck/recovering-unbiased-scene-graphs 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.

interpolate Ran
ran; our contract draft was wrong, not the code
KaihuaTang/Scene-Graph-Benchmark.pytorch/maskrcnn_benchmark/layers/misc.py
pointer only (licence: MIT); the stored copy get_code serves, from KanghoonYoon/torch-rasgg, is pointer only (licence: NONE) · get_code("2902bf4410253ff7")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, KaihuaTang/Scene-Graph-Benchmark.pytorch, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

kl_div_loss Ran
ran; our contract draft was wrong, not the code
KaihuaTang/Scene-Graph-Benchmark.pytorch/maskrcnn_benchmark/layers/kl_div_loss.py
pointer only (licence: MIT); the stored copy get_code serves, from KanghoonYoon/torch-rasgg, is pointer only (licence: NONE) · get_code("382942f3ada73679")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, KaihuaTang/Scene-Graph-Benchmark.pytorch, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 4 later) and 1 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
interpolate 38 other papers
11 dated earlier, 1 the same month, 26 later
1703.06870 (2017-03)
Mask R-CNN
1803.03243 (2018-03)
Domain Adaptive Faster R-CNN for Object Detection in the Wild
1807.08865 (2018-07)
StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction
and 35 more not named here
entropy_loss 10 other papers
10 later
2103.15365 (2021-03)
Visual Distant Supervision for Scene Graph Generation
2201.06794 (2022-01)
Resistance Training Using Prior Bias: Toward Unbiased Scene Graph Generation
2203.09811 (2022-03)
Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation
and 7 more not named here
kl_div_loss 9 other papers
9 later
2103.15365 (2021-03)
Visual Distant Supervision for Scene Graph Generation
2201.06794 (2022-01)
Resistance Training Using Prior Bias: Toward Unbiased Scene Graph Generation
aaai_25356 (2023 (year only))
Learning to Generate an Unbiased Scene Graph by Using Attribute-Guided Predicate Features
and 6 more not named here
build_roi_relation_head 3 other papers
3 later
2106.10815 (2021-06)
Structured Sparse R-CNN for Direct Scene Graph Generation
2107.05080 (2021-07)
Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration
2109.02227 (2021-09)
Learning to Generate Scene Graph from Natural Language Supervision

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

Today's scene graph generation (SGG) task is still far from practical, mainly due to the severe training bias, e.g., collapsing diverse "human walk on / sit on / lay on beach" into "human on beach". Given such SGG, the down-stream tasks such as VQA can hardly infer better scene structures than merely a bag of objects. However, debiasing in SGG is not trivial because traditional debiasing methods cannot distinguish between the good and bad bias, e.g., good context prior (e.g., "person read book" rather than "eat") and bad long-tailed bias (e.g., "near" dominating "behind / in front of"). In this paper, we present a novel SGG framework based on causal inference but not the conventional likelihood. We first build a causal graph for SGG, and perform traditional biased training with the graph. Then, we propose to draw the counterfactual causality from the trained graph to infer the effect from the bad bias, which should be removed. In particular, we use Total Direct Effect (TDE) as the proposed final predicate score for unbiased SGG. Note that our framework is agnostic to any SGG model and thus can be widely applied in the community who seeks unbiased predictions. By using the proposed Scene Graph Diagnosis toolkit on the SGG benchmark Visual Genome and several prevailing models, we observed significant improvements over the previous state-of-the-art methods.

For agents

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

get_harvested_code_for_paper("2002.11949")
get_code_for_paper("2002.11949")
have("2002.11949")

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

curl https://syntology.ai/api/ran/2002.11949.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.11949.svg)](https://syntology.ai/paper/2002.11949)

Connect an agent — have() is free.