Papers › Fine-Grained Scene Graph Generation with Data Transfer
Fine-Grained Scene Graph Generation with Data Transfer
Ao Zhang, Yuan YAO, Qianyu Chen, Wei Ji, Zhiyuan Liu, Maosong Sun, Tat-Seng Chua
Scene graph generation (SGG) is designed to extract (subject, predicate, object) triplets in images. Recent works have made a steady progress on SGG, and provide useful tools for high-level vision and language understanding. However, due to the data distribution problems including long-tail distribution and semantic ambiguity, the predictions of current SGG models tend to collapse to several frequent but uninformative predicates (e.g., on, at), which limits practical application of these models in downstream tasks. To deal with the problems above, we propose a novel Internal and External Data Transfer (IETrans) method, which can be applied in a plug-and-play fashion and expanded to large SGG with 1,807 predicate classes. Our IETrans tries to relieve the data distribution problem by automatically creating an enhanced dataset that provides more sufficient and coherent annotations for all predicates. By training on the enhanced dataset, a Neural Motif model doubles the macro performance while maintaining competitive micro performance. The code and data are publicly available at https://github.com/waxnkw/IETrans-SGG.pytorch.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Scene Graph Generation | Visual Genome | IETrans | Recall@100 | 27.2 | #11 of 19 | Archive leaderboard | report |
| Scene Graph Generation | Visual Genome | IETrans | Recall@50 | 23.5 | #11 of 19 | Archive leaderboard | report |
| Scene Graph Generation | Visual Genome | IETrans | mean Recall @100 | 18.0 | #11 of 19 | Archive leaderboard | report |
| Unbiased Scene Graph Generation | Visual Genome | IETrans (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode) | F@100 | 44.1 | #1 of 31 | Archive leaderboard | report |
| Unbiased Scene Graph Generation | Visual Genome | IETrans (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode) | mR@20 | 28.9 | #1 of 31 | Archive leaderboard | report |
| Unbiased Scene Graph Generation | Visual Genome | IETrans (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode) | ng-mR@20 | 36.0 | #1 of 31 | Archive leaderboard | report |
| Unbiased Scene Graph Generation | Visual Genome | IETrans (MOTIFS-ResNeXt-101-FPN backbone; SGCls mode) | F@100 | 26.0 | #7 of 31 | Archive leaderboard | report |
| Unbiased Scene Graph Generation | Visual Genome | IETrans (MOTIFS-ResNeXt-101-FPN backbone; SGCls mode) | mR@20 | 17.5 | #7 of 31 | Archive leaderboard | report |
| Unbiased Scene Graph Generation | Visual Genome | IETrans (MOTIFS-ResNeXt-101-FPN backbone; SGCls mode) | ng-mR@20 | 21.8 | #7 of 31 | Archive leaderboard | report |
| Unbiased Scene Graph Generation | Visual Genome | IETrans (MOTIFS-ResNeXt-101-FPN backbone; SGDet mode) | F@100 | 21.7 | #14 of 31 | Archive leaderboard | report |
| Unbiased Scene Graph Generation | Visual Genome | IETrans (MOTIFS-ResNeXt-101-FPN backbone; SGDet mode) | mR@20 | 10.9 | #14 of 31 | Archive leaderboard | report |
| Unbiased Scene Graph Generation | Visual Genome | IETrans (MOTIFS-ResNeXt-101-FPN backbone; SGDet mode) | ng-mR@20 | 13.4 | #14 of 31 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
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