Browse State-of-the-Art › Unbiased Scene Graph Generation
Unbiased Scene Graph Generation
16 papers with code · 1 benchmark · 1 dataset archive 2025-07-28
Unbiased Scene Graph Generation (Unbiased SGG) aims to predict more informative scene graphs composed of more "tail predicates" *(in contrast to "head predicates" in terms of class frequencies) by dealing with the skewed, long-tailed predicate class distribution. (Definition from Chiou et al. "Recovering the Unbiased Scene Graphs from the Biased Ones")
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Visual Genome (31 rows) | IETrans (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode) | Fine-Grained Scene Graph Generation with Data Transfer | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
1 dataset whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 30 · with a code link: 16 · where Syntology ran a sample: 6 (5 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (6 of 30 tagged: 5 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 30 of 30, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from.
-
27 Feb 2020 6 repositories listed Syntology official (archive's flag): 3 ran · 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples) · 6 pointer-only (licence)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".
-
1 Apr 2021 4 repositories listedScene graph generation is an important visual understanding task with a broad range of vision applications.
-
22 Mar 2022 2 repositories listedScene graph generation (SGG) is designed to extract (subject, predicate, object) triplets in images.
-
22 Jul 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)The scene graph generation (SGG) task involves detecting objects within an image and predicting predicates that represent the relationships between the objects.
-
23 Aug 2023 1 repository listedWe also propose a self-supervised learning approach to enhance the prediction ability of the tail-prefer feature representation branch by constraining tail-prefer predicate features.
-
18 Aug 2023 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 2 pointer-only (licence)Recent years have seen a growing interest in Scene Graph Generation (SGG), a comprehensive visual scene understanding task that aims to predict entity relationships using a relation encoder-decoder pipeline stacked on…
-
13 Aug 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)Specifically, we first decompose each relation triplet feature into two components: intrinsic feature and extrinsic feature, which correspond to the intrinsic characteristics and extrinsic contexts of a relation…
-
16 Jun 2023 1 repository listedThis paper investigates the problem of scene graph generation in videos with the aim of capturing semantic relations between subjects and objects in the form of ⟨subject, predicate, object⟩ triplets.
-
3 Apr 2023 1 repository listedThe task of dynamic scene graph generation (SGG) from videos is complicated and challenging due to the inherent dynamics of a scene, temporal fluctuation of model predictions, and the long-tailed distribution of the…
-
1 Jan 2023 1 repository listedAn unbiased scene graph generation (SGG) algorithm referred to as Skew Class-balanced Re-weighting (SCR) is proposed for considering the unbiased predicate prediction caused by the long-tailed distribution.
-
16 Jul 2022 1 repository listedExperiments show that our approach achieves a new state-of-the-art performance on VG and GQA datasets and makes a trade-off between the performance of tail predicates and head ones.
-
18 Mar 2022 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 7 pointer-only (licence)Scene Graph Generation, which generally follows a regular encoder-decoder pipeline, aims to first encode the visual contents within the given image and then parse them into a compact summary graph.
-
18 Jan 2022 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)To address this problem, we propose Resistance Training using Prior Bias (RTPB) for the scene graph generation.
-
5 Jul 2021 1 repository listedGiven input images, scene graph generation (SGG) aims to produce comprehensive, graphical representations describing visual relationships among salient objects.
-
16 Sep 2020 1 repository listedWe first build a cognitive structure CogTree to organize the relationships based on the prediction of a biased SGG model.
-
2 Sep 2020 1 repository listedToday, scene graph generation(SGG) task is largely limited in realistic scenarios, mainly due to the extremely long-tailed bias of predicate annotation distribution.
-
Unbiased Scene Graph Generation by Type-Aware Message Passing on Heterogeneous and Dual Graphs20 Nov 2024 0 repositories listedAlthough great progress has been made in the research of unbiased scene graph generation, issues still hinder improving the predictive performance of both head and tail classes.
-
Ensemble Predicate Decoding for Unbiased Scene Graph Generation26 Aug 2024 0 repositories listedScene Graph Generation (SGG) aims to generate a comprehensive graphical representation that accurately captures the semantic information of a given scenario.
-
ALF: Adaptive Label Finetuning for Scene Graph Generation29 Dec 2023 0 repositories listedScene Graph Generation (SGG) endeavors to predict the relationships between subjects and objects in a given image.
-
FloCoDe: Unbiased Dynamic Scene Graph Generation with Temporal Consistency and Correlation Debiasing24 Oct 2023 0 repositories listedDynamic scene graph generation (SGG) from videos requires not only a comprehensive understanding of objects across scenes but also a method to capture the temporal motions and interactions with different objects.
-
Generalized Unbiased Scene Graph Generation9 Aug 2023 0 repositories listedExisting Unbiased Scene Graph Generation (USGG) methods only focus on addressing the predicate-level imbalance that high-frequency classes dominate predictions of rare ones, while overlooking the concept-level imbalance.
-
Unbiased Scene Graph Generation via Two-stage Causal Modeling11 Jul 2023 0 repositories listedDespite the impressive performance of recent unbiased Scene Graph Generation (SGG) methods, the current debiasing literature mainly focuses on the long-tailed distribution problem, whereas it overlooks another source of…
-
Peer Learning for Unbiased Scene Graph Generation31 Dec 2022 0 repositories listedUnbiased scene graph generation (USGG) is a challenging task that requires predicting diverse and heavily imbalanced predicates between objects in an image.
-
Unbiased Scene Graph Generation using Predicate Similarities3 Oct 2022 0 repositories listedScene Graphs are widely applied in computer vision as a graphical representation of relationships between objects shown in images.
-
Context-aware Mixture-of-Experts for Unbiased Scene Graph Generation15 Aug 2022 0 repositories listedScene graph generation (SGG) has gained tremendous progress in recent years.
-
Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation7 Aug 2022 0 repositories listedThe Scene Graph Generation (SGG) task aims to detect all the objects and their pairwise visual relationships in a given image.
-
Rethinking the Evaluation of Unbiased Scene Graph Generation3 Aug 2022 0 repositories listedCurrent Scene Graph Generation (SGG) methods tend to predict frequent predicate categories and fail to recognize rare ones due to the severe imbalanced distribution of predicates.
-
Learning Structured Representations of Visual Scenes9 Jul 2022 0 repositories listedAs the intermediate-level representations bridging the two levels, structured representations of visual scenes, such as visual relationships between pairwise objects, have been shown to not only benefit compositional…
-
PPDL: Predicate Probability Distribution Based Loss for Unbiased Scene Graph Generation1 Jan 2022 0 repositories listedScene Graph Generation (SGG) has attracted more and more attention from visual researchers in recent years, since Scene Graph (SG) is valuable in many downstream tasks due to its rich structural-semantic details.
-
Unbiased Scene Graph Generation via Rich and Fair Semantic Extraction1 Feb 2020 0 repositories listedExtracting graph representation of visual scenes in image is a challenging task in computer vision.
Syntology lines on 6 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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