Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation

By Yifan Feng, Jian Huang, Shaoyi Du, Shihui Ying, Jun-Hai Yong, Yipeng Li, Guiguang Ding, Rongrong Ji, Yue Gao. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024

332 citations recorded by the source corpus.

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% <inline-formula><tex-math notation="LaTeX">$\text{AP}^{val}$</tex-math><alternatives><mml:math><mml:msup><mml:mtext>AP</mml:mtext><mml:mrow><mml:mi>v</mml:mi><mml:mi>a</mml:mi><mml:mi>l</mml:mi></mml:mrow></mml:msup></mml:math><inline-graphic xlink:href="feng-ieq1-3524377.gif"/></alternatives></inline-formula> and 9% <inline-formula><tex-math notation="LaTeX">$\text{AP}^{val}$</tex-math><alternatives><mml:math><mml:msup><mml:mtext>AP</mml:mtext><mml:mrow><mml:mi>v</mml:mi><mml:mi>a</mml:mi><mml:mi>l</mml:mi></mml:mrow></mml:msup></mml:math><inline-graphic xlink:href="feng-ieq2-3524377.gif"/></alternatives></inline-formula> improvements.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a277826066a242733419a1fbb472cc7241902a9b

Citations in the corpus