UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913643542609920 |
|---|---|
| author | Liao, Xinyao Wei, Wei Chen, Dangyang Fu, Yuanyuan |
| author_facet | Liao, Xinyao Wei, Wei Chen, Dangyang Fu, Yuanyuan |
| contents | Scene Graph Generation(SGG) is a scene understanding task that aims at identifying object entities and reasoning their relationships within a given image. In contrast to prevailing two-stage methods based on a large object detector (e.g., Faster R-CNN), one-stage methods integrate a fixed-size set of learnable queries to jointly reason relational triplets <subject, predicate, object>. This paradigm demonstrates robust performance with significantly reduced parameters and computational overhead. However, the challenge in one-stage methods stems from the issue of weak entanglement, wherein entities involved in relationships require both coupled features shared within triplets and decoupled visual features. Previous methods either adopt a single decoder for coupled triplet feature modeling or multiple decoders for separate visual feature extraction but fail to consider both. In this paper, we introduce UniQ, a Unified decoder with task-specific Queries architecture, where task-specific queries generate decoupled visual features for subjects, objects, and predicates respectively, and unified decoder enables coupled feature modeling within relational triplets. Experimental results on the Visual Genome dataset demonstrate that UniQ has superior performance to both one-stage and two-stage methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05687 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generation Liao, Xinyao Wei, Wei Chen, Dangyang Fu, Yuanyuan Computer Vision and Pattern Recognition I.2.10 Scene Graph Generation(SGG) is a scene understanding task that aims at identifying object entities and reasoning their relationships within a given image. In contrast to prevailing two-stage methods based on a large object detector (e.g., Faster R-CNN), one-stage methods integrate a fixed-size set of learnable queries to jointly reason relational triplets <subject, predicate, object>. This paradigm demonstrates robust performance with significantly reduced parameters and computational overhead. However, the challenge in one-stage methods stems from the issue of weak entanglement, wherein entities involved in relationships require both coupled features shared within triplets and decoupled visual features. Previous methods either adopt a single decoder for coupled triplet feature modeling or multiple decoders for separate visual feature extraction but fail to consider both. In this paper, we introduce UniQ, a Unified decoder with task-specific Queries architecture, where task-specific queries generate decoupled visual features for subjects, objects, and predicates respectively, and unified decoder enables coupled feature modeling within relational triplets. Experimental results on the Visual Genome dataset demonstrate that UniQ has superior performance to both one-stage and two-stage methods. |
| title | UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generation |
| topic | Computer Vision and Pattern Recognition I.2.10 |
| url | https://arxiv.org/abs/2501.05687 |