Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.14270 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913436259057664 |
|---|---|
| author | Salzmann, Tim Ryll, Markus Bewley, Alex Minderer, Matthias |
| author_facet | Salzmann, Tim Ryll, Markus Bewley, Alex Minderer, Matthias |
| contents | Visual relationship detection aims to identify objects and their relationships in images. Prior methods approach this task by adding separate relationship modules or decoders to existing object detection architectures. This separation increases complexity and hinders end-to-end training, which limits performance. We propose a simple and highly efficient decoder-free architecture for open-vocabulary visual relationship detection. Our model consists of a Transformer-based image encoder that represents objects as tokens and models their relationships implicitly. To extract relationship information, we introduce an attention mechanism that selects object pairs likely to form a relationship. We provide a single-stage recipe to train this model on a mixture of object and relationship detection data. Our approach achieves state-of-the-art relationship detection performance on Visual Genome and on the large-vocabulary GQA benchmark at real-time inference speeds. We provide ablations, real-world qualitative examples, and analyses of zero-shot performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_14270 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection Salzmann, Tim Ryll, Markus Bewley, Alex Minderer, Matthias Computer Vision and Pattern Recognition Computation and Language Machine Learning Robotics Visual relationship detection aims to identify objects and their relationships in images. Prior methods approach this task by adding separate relationship modules or decoders to existing object detection architectures. This separation increases complexity and hinders end-to-end training, which limits performance. We propose a simple and highly efficient decoder-free architecture for open-vocabulary visual relationship detection. Our model consists of a Transformer-based image encoder that represents objects as tokens and models their relationships implicitly. To extract relationship information, we introduce an attention mechanism that selects object pairs likely to form a relationship. We provide a single-stage recipe to train this model on a mixture of object and relationship detection data. Our approach achieves state-of-the-art relationship detection performance on Visual Genome and on the large-vocabulary GQA benchmark at real-time inference speeds. We provide ablations, real-world qualitative examples, and analyses of zero-shot performance. |
| title | Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection |
| topic | Computer Vision and Pattern Recognition Computation and Language Machine Learning Robotics |
| url | https://arxiv.org/abs/2403.14270 |