Multi-level Compositional Feature Augmentation for Unbiased Scene Graph Generation
International Journal of Computer Vision · 2026-06 · 134 (6)
DOI: 10.1007/s11263-026-02855-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 01.06.2026. Verfasst von Lin Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Hong Kong Government, Innovation and Technology Commission - Hong Kong.
Abstract (Originalsprache)
Scene Graph Generation (SGG) aims to detect all the visual relation triplets in a given image. With the emergence of various advanced techniques for better utilizing both the intrinsic and extrinsic information in each relation triplet, SGG has achieved great progress over the recent years. However, due to the ubiquitous long-tailed predicate distributions, today’s SGG models are still easily biased to the head predicates. Currently, the most prevalent debiasing solutions for SGG are re-balancing methods, e . g ., changing the distributions of original training samples. In this paper, we argue that all existing re-balancing strategies fail to increase the diversity of the relation triplet features of each predicate, which is critical for robust SGG. To this end, we propose a novel M ulti-level C ompositional F eature A ugmentation ( MCFA ) strategy, which aims to mitigate the bias issue from the perspective of increasing the diversity of triplet features. Specifically, we enhance relationship diversity on not only feature-level , i . e ., replacing the intrinsic or extrinsic visual features of triplets with other correlated samples to create novel feature compositions for tail predicates, but also image-level , i . e ., manipulating the image to generate brand new visual appearance for triplets. Due to its model-agnostic nature, MCFA can be seamlessly incorporated into various SGG frameworks. Extensive ablations have shown that MCFA achieves a new state-of-the-art performance on the trade-off between different metrics.
Förderung
- National Natural Science Foundation of China
- Hong Kong Government
- Innovation and Technology Commission - Hong Kong
- Tencent
Zitieren
APA
Li, L., Li, X., Sun, C., Li, C., & Chen, L. (2026). Multi-level Compositional Feature Augmentation for Unbiased Scene Graph Generation. International Journal of Computer Vision, 134(6). https://doi.org/10.1007/s11263-026-02855-7
Vancouver
Li L, Li X, Sun C, Li C, Chen L. Multi-level Compositional Feature Augmentation for Unbiased Scene Graph Generation. International Journal of Computer Vision. 2026;134(6). doi:10.1007/s11263-026-02855-7
BibTeX
@article{Li2026,
author = {Li, Lin and Li, Xingchen and Sun, Chong and Li, Chen and Chen, Long},
title = {Multi-level Compositional Feature Augmentation for Unbiased Scene Graph Generation},
journal = {International Journal of Computer Vision},
year = {2026},
volume = {134},
number = {6},
doi = {10.1007/s11263-026-02855-7}
}
EUVIMED