Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation

Yifan Feng, Jiangang Huang, Shaoyi Du, Shihui Ying, Jun-Hai Yong, Yipeng Li, Guiguang Ding, Rongrong Ji, Yue Gao

TL;DR

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, enables the model to acquire both semantic and structural information, advancing beyond conventional feature-focused learning.

Abstract

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.

Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation

TL;DR

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, enables the model to acquire both semantic and structural information, advancing beyond conventional feature-focused learning.

Abstract

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\% and 9\% improvements. The source codes are at ttps://github.com/iMoonLab/Hyper-YOLO.
Paper Structure (40 sections, 6 equations, 8 figures, 11 tables)

This paper contains 40 sections, 6 equations, 8 figures, 11 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. YOLO Series Object Detectors
  4. Hypergraph Learning Methods
  5. Hypergraph Computation Empowered Semantic Collecting and Scattering Framework
  6. Methods
  7. Preliminaries
  8. Hyper-YOLO Overview
  9. Mixed Aggregation Network
  10. Hypergraph-Based Cross-Level and Cross-Position Representation Network
  11. Hypergraph Construction.
  12. Hypergraph Convolution.
  13. An Instance of HGC-SCS Framework.
  14. Comparison and Analysis
  15. Experiments
  16. ...and 25 more sections

Figures (8)

  • Figure 1: Comparison with other SOTA YOLO series methods on the COCO.
  • Figure 2: Illustration of the proposed Mixed Aggregation Network (MANet).
  • Figure 3: Illstration of hypergraph construction.
  • Figure 4: Illstration of the proposed Hypergraph-Based Cross-Level and Cross-Position Representation Network (HyperC2Net).
  • Figure 5: Visualization of feature maps before and after high-order learning.
  • ...and 3 more figures