Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911372380471296 |
|---|---|
| author | Qu, Runfeng Hall, Ole Bideau, Pia K Ouerfelli-Ethier, Julie Rolfs, Martin Obermayer, Klaus Hellwich, Olaf |
| author_facet | Qu, Runfeng Hall, Ole Bideau, Pia K Ouerfelli-Ethier, Julie Rolfs, Martin Obermayer, Klaus Hellwich, Olaf |
| contents | Scene Graph Generation (SGG) suffers from a long-tailed distribution, where a few predicate classes dominate while many others are underrepresented, leading to biased models that underperform on rare relations. Unbiased-SGG methods address this issue by implementing debiasing strategies, but often at the cost of spatial understanding, resulting in an over-reliance on semantic priors. We introduce Salience-SGG, a novel framework featuring an Iterative Salience Decoder (ISD) that emphasizes triplets with salient spatial structures. To support this, we propose semantic-agnostic salience labels guiding ISD. Evaluations on Visual Genome, Open Images V6, and GQA-200 show that Salience-SGG achieves state-of-the-art performance and improves existing Unbiased-SGG methods in their spatial understanding as demonstrated by the Pairwise Localization Average Precision |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_08728 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimation Qu, Runfeng Hall, Ole Bideau, Pia K Ouerfelli-Ethier, Julie Rolfs, Martin Obermayer, Klaus Hellwich, Olaf Computer Vision and Pattern Recognition Scene Graph Generation (SGG) suffers from a long-tailed distribution, where a few predicate classes dominate while many others are underrepresented, leading to biased models that underperform on rare relations. Unbiased-SGG methods address this issue by implementing debiasing strategies, but often at the cost of spatial understanding, resulting in an over-reliance on semantic priors. We introduce Salience-SGG, a novel framework featuring an Iterative Salience Decoder (ISD) that emphasizes triplets with salient spatial structures. To support this, we propose semantic-agnostic salience labels guiding ISD. Evaluations on Visual Genome, Open Images V6, and GQA-200 show that Salience-SGG achieves state-of-the-art performance and improves existing Unbiased-SGG methods in their spatial understanding as demonstrated by the Pairwise Localization Average Precision |
| title | Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.08728 |