SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.15365 · ICCV · 2021

Visual Distant Supervision for Scene Graph Generation

Maosong Sun, Zhiyuan Liu, Xu Han, Yuan Yao, Mengdi Li, Cornelius Weber, Stefan Wermter, Ao Zhang

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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; 5 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/2103.15365.json · badge: /api/ran/2103.15365.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
thunlp/VisualDS canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
entropy_loss Ran
ran; our contract draft was wrong, not the code
thunlp/VisualDS/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: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from KanghoonYoon/torch-rasgg, and GitHub detected no licence in that repository 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
thunlp/VisualDS/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: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from KanghoonYoon/torch-rasgg, and GitHub detected no licence in that repository 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.

kl_div_loss Ran
ran; our contract draft was wrong, not the code
thunlp/VisualDS/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: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from KanghoonYoon/torch-rasgg, and GitHub detected no licence in that repository 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.

sigmoid_focal_loss_cpu Ran
ran; our contract draft was wrong, not the code
thunlp/VisualDS/maskrcnn_benchmark/layers/sigmoid_focal_loss.py
pointer only (licence: MIT); the stored copy get_code serves, from KanghoonYoon/torch-rasgg, is pointer only (licence: NONE) · get_code("426fd02a2beaf826")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from KanghoonYoon/torch-rasgg, and GitHub detected no licence in that repository 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.

smooth_l1_loss Ran
ran; our contract draft was wrong, not the code
thunlp/VisualDS/maskrcnn_benchmark/layers/smooth_l1_loss.py
code served (permissive licence) · get_code("e261fa29066b37e5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small tensors for input and target
input_tensor = torch.randn(2, 4)
target_tensor = torch.randn(2, 4)

# Create ARGS dict with all parameters
ARGS = {
    "input": input_tensor,
    "target": target_tensor,
    "beta": 1.0 / 9,
    "size_average": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 5 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
interpolate 38 other papers
17 dated earlier, 1 the same month, 20 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
smooth_l1_loss 16 other papers
10 dated earlier, 6 later
1703.06870 (2017-03)
Mask R-CNN
1903.00241 (2019-03)
Mask Scoring R-CNN
1904.01169 (2019-04)
Res2Net: A New Multi-scale Backbone Architecture
and 13 more not named here
entropy_loss 10 other papers
1 dated earlier, 9 later
2002.11949 (2020-02)
Unbiased Scene Graph Generation from Biased Training
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
sigmoid_focal_loss_cpu 10 other papers
6 dated earlier, 4 later
1803.03243 (2018-03)
Domain Adaptive Faster R-CNN for Object Detection in the Wild
1904.01169 (2019-04)
Res2Net: A New Multi-scale Backbone Architecture
1904.01355 (2019-04)
FCOS: Fully Convolutional One-Stage Object Detection
and 7 more not named here
kl_div_loss 9 other papers
1 dated earlier, 8 later
2002.11949 (2020-02)
Unbiased Scene Graph Generation from Biased Training
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

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

Scene graph generation aims to identify objects and their relations in images, providing structured image representations that can facilitate numerous applications in computer vision. However, scene graph models usually require supervised learning on large quantities of labeled data with intensive human annotation. In this work, we propose visual distant supervision, a novel paradigm of visual relation learning, which can train scene graph models without any human-labeled data. The intuition is that by aligning commonsense knowledge bases and images, we can automatically create large-scale labeled data to provide distant supervision for visual relation learning. To alleviate the noise in distantly labeled data, we further propose a framework that iteratively estimates the probabilistic relation labels and eliminates the noisy ones. Comprehensive experimental results show that our distantly supervised model outperforms strong weakly supervised and semi-supervised baselines. By further incorporating human-labeled data in a semi-supervised fashion, our model outperforms state-ofthe-art fully supervised models by a large margin (e.g., 8.3 micro-and 7.8 macro-recall@50 improvements for predicate classification in Visual Genome evaluation). We make the data and code for this paper publicly available at https://github.com/thunlp/VisualDS.

For agents

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

get_harvested_code_for_paper("2103.15365")
get_code_for_paper("2103.15365")
have("2103.15365")

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

curl https://syntology.ai/api/ran/2103.15365.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.15365.svg)](https://syntology.ai/paper/2103.15365)

Connect an agent — have() is free.