Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912074190290944 |
|---|---|
| author | Feng, Yifan Huang, Jiangang Du, Shaoyi Ying, Shihui Yong, Jun-Hai Li, Yipeng Ding, Guiguang Ji, Rongrong Gao, Yue |
| author_facet | Feng, Yifan Huang, Jiangang Du, Shaoyi Ying, Shihui Yong, Jun-Hai Li, Yipeng Ding, Guiguang Ji, Rongrong Gao, Yue |
| contents | We introduce Hyper-YOLO, a new object detection method that integrates hypergraph computations to capture the complex high-order correlations among visual features. Traditional YOLO models, while powerful, have limitations in their neck designs that restrict the integration of cross-level features and the exploitation of high-order feature interrelationships. To address these challenges, we propose the Hypergraph Computation Empowered Semantic Collecting and Scattering (HGC-SCS) framework, which transposes visual feature maps into a semantic space and constructs a hypergraph for high-order message propagation. This enables the model to acquire both semantic and structural information, advancing beyond conventional feature-focused learning. Hyper-YOLO incorporates the proposed Mixed Aggregation Network (MANet) in its backbone for enhanced feature extraction and introduces the Hypergraph-Based Cross-Level and Cross-Position Representation Network (HyperC2Net) in its neck. HyperC2Net operates across five scales and breaks free from traditional grid structures, allowing for sophisticated high-order interactions across levels and positions. This synergy of components positions Hyper-YOLO as a state-of-the-art architecture in various scale models, as evidenced by its superior performance on the COCO dataset. Specifically, Hyper-YOLO-N significantly outperforms the advanced YOLOv8-N and YOLOv9-T with 12\% $\text{AP}^{val}$ and 9\% $\text{AP}^{val}$ improvements. The source codes are at ttps://github.com/iMoonLab/Hyper-YOLO. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_04804 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation Feng, Yifan Huang, Jiangang Du, Shaoyi Ying, Shihui Yong, Jun-Hai Li, Yipeng Ding, Guiguang Ji, Rongrong Gao, Yue Computer Vision and Pattern Recognition We introduce Hyper-YOLO, a new object detection method that integrates hypergraph computations to capture the complex high-order correlations among visual features. Traditional YOLO models, while powerful, have limitations in their neck designs that restrict the integration of cross-level features and the exploitation of high-order feature interrelationships. To address these challenges, we propose the Hypergraph Computation Empowered Semantic Collecting and Scattering (HGC-SCS) framework, which transposes visual feature maps into a semantic space and constructs a hypergraph for high-order message propagation. This enables the model to acquire both semantic and structural information, advancing beyond conventional feature-focused learning. Hyper-YOLO incorporates the proposed Mixed Aggregation Network (MANet) in its backbone for enhanced feature extraction and introduces the Hypergraph-Based Cross-Level and Cross-Position Representation Network (HyperC2Net) in its neck. HyperC2Net operates across five scales and breaks free from traditional grid structures, allowing for sophisticated high-order interactions across levels and positions. This synergy of components positions Hyper-YOLO as a state-of-the-art architecture in various scale models, as evidenced by its superior performance on the COCO dataset. Specifically, Hyper-YOLO-N significantly outperforms the advanced YOLOv8-N and YOLOv9-T with 12\% $\text{AP}^{val}$ and 9\% $\text{AP}^{val}$ improvements. The source codes are at ttps://github.com/iMoonLab/Hyper-YOLO. |
| title | Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.04804 |