Papers › EGTR: Extracting Graph from Transformer for Scene Graph Generation

EGTR: Extracting Graph from Transformer for Scene Graph Generation

2 Apr 2024CVPR 2024 1arXiv:2404.02072archive 2025-07-28

Jinbae Im, Jeongyeon Nam, Nokyung Park, HyungMin Lee, Seunghyun Park

Scene Graph Generation (SGG) is a challenging task of detecting objects and predicting relationships between objects. After DETR was developed, one-stage SGG models based on a one-stage object detector have been actively studied. However, complex modeling is used to predict the relationship between objects, and the inherent relationship between object queries learned in the multi-head self-attention of the object detector has been neglected. We propose a lightweight one-stage SGG model that extracts the relation graph from the various relationships learned in the multi-head self-attention layers of the DETR decoder. By fully utilizing the self-attention by-products, the relation graph can be extracted effectively with a shallow relation extraction head. Considering the dependency of the relation extraction task on the object detection task, we propose a novel relation smoothing technique that adjusts the relation label adaptively according to the quality of the detected objects. By the relation smoothing, the model is trained according to the continuous curriculum that focuses on object detection task at the beginning of training and performs multi-task learning as the object detection performance gradually improves. Furthermore, we propose a connectivity prediction task that predicts whether a relation exists between object pairs as an auxiliary task of the relation extraction. We demonstrate the effectiveness and efficiency of our method for the Visual Genome and Open Image V6 datasets. Our code is publicly available at https://github.com/naver-ai/egtr.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 17 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 2 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 16 ran (7 with no instrument failure; 9 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

naver-ai/egtr officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 17 samples, 16 ran (9 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

17 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 2 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
2ran · violated contract
7ran · our draft was wrong
2ran; the contract check could not run
3ran
1unverified

Licence: 4 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from naver-ai/egtr. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

naver-ai/egtr official repository 17 samples, 16 ran (9 instrument-failed) · 1 unverified
argsort_desc in 6 papers lib/pytorch_misc.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 7d4002289969a288 · report fixture: signature scores:ndarray/2/float · returned ndarray · level recorded 2026-09-25
bbox_iou in 21 papers lib/evaluation/ap_eval_rel.py ran · violated contract Apache-2.0 (permissive) · 8b29521250c9137c · report fixture: signature box1:ndarray/2/float, box2:ndarray/2/float · returned Tensor · level recorded 2026-09-24
box_area in 11 papers model/util.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · d642ed19bfc91106 · report fixture: signature boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-25
build_position_encoding in 42 papers model/deformable_detr.py ran · our draft was wrong Apache-2.0 (permissive) · 72ceaeb9390c2de9 · report fixture: signature config:Config/0/? · returned DeformableDetrSinePositionEmbedding · level recorded 2026-09-25
collate_fn in 500 papers train_egtr.py ran Apache-2.0 (permissive) · cdb6e23f77eb4b45 · report fixture: signature batch:list/1/tuple, feature_extractor:MinimalFeatureExtractor/0/? · returned dict · level recorded 2026-09-25
convert_to_xywh in 26 papers lib/evaluation/coco_eval.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · f31a58bf6457ced5 · report fixture: signature boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-22
crop in 99 papers
census: 5 implementations from 5 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
model/transform.py ran Apache-2.0 (permissive) · 2c3f120011363d96 · report fixture: signature image:Image/0/?, target:dict/0/?, region:tuple/1/int · returned tuple · level recorded 2026-09-25
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
model/util.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · ca18559102973d9c · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_boxes:int/0/int · returned Tensor · level recorded 2026-09-25
evaluate in 514 papers lib/evaluation/coco_eval.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · fe0ddcc2d420c9a0 · report fixture: signature self:MockCOCOEval/0/? · returned tuple · level recorded 2026-09-22
get_ap lib/evaluation/ap_eval_rel.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 68d0b7c3f3d24968 · report fixture: signature rec:ndarray/1/float, prec:ndarray/1/float · returned float64 · level recorded 2026-09-24
hflip in 29 papers model/transform.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 9be9e658b5bd688a · report fixture: signature image:Image/0/?, target:dict/0/? · returned tuple · level recorded 2026-09-24
intersect_2d in 7 papers lib/pytorch_misc.py ran · violated contract Apache-2.0 (permissive) · 6727d2d8f1d79998 · report fixture: signature x1:ndarray/2/int, x2:ndarray/2/int · returned ndarray · level recorded 2026-09-25
inverse_sigmoid in 80 papers
census: 9 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
model/deformable_detr.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 83c03ceb1307c6c4 · report fixture: signature x:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
ms_deform_attn_core_pytorch in 7 papers model/deformable_detr.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · c53ec291fabfc643 · report fixture: signature value:Tensor/4/float, value_spatial_shapes:list/1/tuple, sampling_locations:Tensor/6/float, attention_weights:Tensor/5/float · returned Tensor · level recorded 2026-09-22
prepare_mAP_dets lib/evaluation/ap_eval_rel.py ran Apache-2.0 (permissive) · 407320cfdd98192d · report fixture: signature topk_dets:list/1/dict, cls_num:int/0/int · returned tuple · level recorded 2026-09-24
sigmoid_focal_loss in 122 papers
census: 3 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
model/util.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 728119ce133dfec1 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_boxes:int/0/int, alpha:float/0/float, gamma:float/0/float · returned Tensor · level recorded 2026-09-25
eval_rel_results lib/evaluation/oi_eval.py unverified Apache-2.0 (permissive) · e38b3656e1c52b5c · report

Tasks

Graph GenerationMulti-Task LearningObjectObject DetectionRelation ExtractionScene Graph Generationobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEConvolutionDense ConnectionsDetrDropoutFeedforward NetworkLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections