Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation

• URL: http://arxiv.org/abs/2408.04804v2
• Date: Wed, 16 Oct 2024 07:20:58 GMT
• Title: Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation
• Authors: Yifan Feng, Jiangang Huang, Shaoyi Du, Shihui Ying, Jun-Hai Yong, Yipeng Li, Guiguang Ding, Rongrong Ji, Yue Gao,
• Abstract summary: We introduce a new object detection method that integrates hypergraph computations to capture the complex high-order correlations among visual features. Hyper-YOLO significantly outperforms the advanced YOLOv8-N and YOLOv9T with 12% $textval$ and 9% $APMoonLab improvements.
• Score: 74.65906322148997
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model [88.13261547704444]
  Hyper SIGMA is a vision transformer-based foundation model for HSI interpretation. It integrates spatial and spectral features using a specially designed spectral enhancement module. It shows significant advantages in scalability, robustness, cross-modal transferring capability, and real-world applicability.
  arXiv  Detail & Related papers  (2024-06-17T13:22:58Z)
• Hypergraph Transformer for Semi-Supervised Classification [50.92027313775934]
  We propose a novel hypergraph learning framework, HyperGraph Transformer (HyperGT) HyperGT uses a Transformer-based neural network architecture to effectively consider global correlations among all nodes and hyperedges. It achieves comprehensive hypergraph representation learning by effectively incorporating global interactions while preserving local connectivity patterns.
  arXiv  Detail & Related papers  (2023-12-18T17:50:52Z)
• Self-Supervised Pretraining for Heterogeneous Hypergraph Neural Networks [9.987252149421982]
  We present a novel self-supervised pretraining framework for heterogeneous HyperGNNs. Our method is able to effectively capture higher-order relations among entities in the data in a self-supervised manner. Our experiments show that our proposed framework consistently outperforms state-of-the-art baselines in various downstream tasks.
  arXiv  Detail & Related papers  (2023-11-19T16:34:56Z)
• A Unified View Between Tensor Hypergraph Neural Networks And Signal Denoising [7.083679120873857]
  We show that the tensor-hypergraph convolutional network (T-HGCN) has emerged as a powerful architecture for preserving higher-order interactions on hypergraphs. We further design a tensor-hypergraph iterative network (T-HGIN) based on the HyperGSD problem, which takes advantage of a multi-step updating scheme in every single layer.
  arXiv  Detail & Related papers  (2023-09-15T13:19:31Z)
• From Hypergraph Energy Functions to Hypergraph Neural Networks [94.88564151540459]
  We present an expressive family of parameterized, hypergraph-regularized energy functions. We then demonstrate how minimizers of these energies effectively serve as node embeddings. We draw parallels between the proposed bilevel hypergraph optimization, and existing GNN architectures in common use.
  arXiv  Detail & Related papers  (2023-06-16T04:40:59Z)
• Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative [126.0985540285981]
  We apply the contrastive learning approach from images/graphs (we refer to it as HyperGCL) to improve generalizability of hypergraph neural networks. We fabricate two schemes to augment hyperedges with higher-order relations encoded, and adopt three augmentation strategies from graph-structured data. We propose a hypergraph generative model to generate augmented views, and then an end-to-end differentiable pipeline to jointly learn hypergraph augmentations and model parameters.
  arXiv  Detail & Related papers  (2022-10-07T20:12:20Z)
• Residual Enhanced Multi-Hypergraph Neural Network [26.42547421121713]
  HyperGraph Neural Network (HGNN) is the de-facto method for hypergraph representation learning. We propose the Residual enhanced Multi-Hypergraph Neural Network, which can fuse multi-modal information from each hypergraph effectively.
  arXiv  Detail & Related papers  (2021-05-02T14:53:32Z)
• HNHN: Hypergraph Networks with Hyperedge Neurons [90.15253035487314]
  HNHN is a hypergraph convolution network with nonlinear activation functions applied to both hypernodes and hyperedges. We demonstrate improved performance of HNHN in both classification accuracy and speed on real world datasets when compared to state of the art methods.
  arXiv  Detail & Related papers  (2020-06-22T14:08:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.