SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.02597 · CVPR · 2022

Fine-Grained Predicates Learning for Scene Graph Generation

Zhou Zhao, Jingkuan Song, Lianli Gao, Heng Shen, Xinyu Lyu, Hao Huang, Yuyu Guo

arXiv · PDF · Open in the Atlas

Code that ran

9 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 4 have no contract verdict; 4 failures of our instrument; 1 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/2204.02597.json · badge: /api/ran/2204.02597.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
xinyulyu/fgpl marked official in Papers with Code
Papers with Code archive
9 ran · 1 no recorded run
FunctionStatusWhere it lives
Label_Smoothing_Regression Ran
ran on a synthesized input · constructed an object; no result was computed
xinyulyu/fgpl/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py
pointer only (licence: NONE) · get_code("51831c7bffebd292")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xinyulyu/fgpl 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.

MyCrossEntropyLoss Ran
ran on a synthesized input
xinyulyu/fgpl/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py
pointer only (licence: NONE) · get_code("2249d096c9f89ccd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xinyulyu/fgpl 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.

TripletLoss Ran
ran on a synthesized input · constructed an object; no result was computed
xinyulyu/fgpl/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py
pointer only (licence: NONE) · get_code("b33af276d20651f6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xinyulyu/fgpl 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.

TripletLoss_CB Ran
ran on a synthesized input · constructed an object; no result was computed
xinyulyu/fgpl/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py
pointer only (licence: NONE) · get_code("5a1f8b1aa2cee093")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xinyulyu/fgpl 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.

adj_laplacian Ran
ran, violated the contract we drafted
xinyulyu/fgpl/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py
pointer only (licence: NONE) · get_code("2dac2d9248237ad8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xinyulyu/fgpl 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.

cat Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xinyulyu/fgpl/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py
pointer only (licence: NONE) · get_code("6cbf46794989b731")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xinyulyu/fgpl 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.

log_weighted_softmax Ran
ran; our contract draft was wrong, not the code
xinyulyu/fgpl/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py
pointer only (licence: NONE) · get_code("52d56edd43f3dbf5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xinyulyu/fgpl 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.

normalize Ran
ran; our contract draft was wrong, not the code
xinyulyu/fgpl/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py
pointer only (licence: NONE) · get_code("0b1e1f4052f5c5e4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xinyulyu/fgpl 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.

predicate_statistics Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xinyulyu/fgpl/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py
pointer only (licence: NONE) · get_code("de4f39fa50cb72f7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xinyulyu/fgpl 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.

RelationLossComputation Not yet run
unverified (harvested, no recorded run)
xinyulyu/fgpl/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py
pointer only (licence: NONE) · get_code("27df07933d843d50")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xinyulyu/fgpl 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. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 8 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
cat
brick of this paper's assembly: helper
18 other papers
7 dated earlier, 10 later, 1 same year, order not determinable · 3 only as an assembly brick
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1908.07836 (2019-08)
PubLayNet: largest dataset ever for document layout analysis
2002.10111 (2020-02)
SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
and 15 more not named here
Label_Smoothing_Regression
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2206.03014 (2022-06)
The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation

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

The performance of current Scene Graph Generation models is severely hampered by some hard-to-distinguish predicates, e.g., "woman-on/standing on/walking onbeach" or "woman-near/looking at/in front of-child". While general SGG models are prone to predict head predicates and existing re-balancing strategies prefer tail categories, none of them can appropriately handle these hard-to-distinguish predicates. To tackle this issue, inspired by fine-grained image classification, which focuses on differentiating among hard-to-distinguish object classes, we propose a method named Fine-Grained Predicates Learning (FGPL) which aims at differentiating among hard-to-distinguish predicates for Scene Graph Generation task. Specifically, we first introduce a Predicate Lattice that helps SGG models to figure out fine-grained predicate pairs. Then, utilizing the Predicate Lattice, we propose a Category Discriminating Loss and an Entity Discriminating Loss, which both contribute to distinguishing fine-grained predicates while maintaining learned discriminatory power over recognizable ones. The proposed model-agnostic strategy significantly boosts the performances of three benchmark models (Transformer, VCTree, and Motif) by 22.8%, 24.1% and 21.7% of Mean Recall (mR@100) on the Predicate Classification sub-task, respectively. Our model also outperforms state-of-the-art methods by a large margin (i.e., 6.1%, 4.6%, and 3.2% of Mean Recall (mR@100)) on the Visual Genome dataset. Codes are publicly available 1 .

For agents

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

get_harvested_code_for_paper("2204.02597")
get_code_for_paper("2204.02597")
have("2204.02597")

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

curl https://syntology.ai/api/ran/2204.02597.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.02597.svg)](https://syntology.ai/paper/2204.02597)

Connect an agent — have() is free.