YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception

2025-06-21

AI Summary

YOLO architectures are constrained by the locality of convolutional operations and the pairwise modeling limitation of regional self-attention, hindering effective capture of global, many-to-many, higher-order correlations—thus degrading detection performance in complex scenes. To address this, we propose YOLOv13, introducing two core innovations: (1) Hypergraph-Augmented Adaptive Contextual Enhancement (HyperACE), enabling cross-location and cross-scale higher-order relational modeling; and (2) Full-Pipeline Adaptive Distillation (FullPAD), facilitating fine-grained feature collaboration across the entire detection pipeline. Leveraging hypergraph computation, depthwise separable convolutions, and lightweight large-kernel designs, our modules achieve superior representational capacity with significantly reduced parameters and FLOPs. On MS COCO, YOLOv13 establishes new state-of-the-art performance: YOLOv13-N achieves +3.0% and +1.5% mAP over YOLOv11-N and YOLOv12-N, respectively.

Technology Category

• Computer Vision: Large Vision Models
• Machine Learning: Deep Neural Architectures and Foundation Models
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The YOLO series models reign supreme in real-time object detection due to their superior accuracy and computational efficiency. However, both the convolutional architectures of YOLO11 and earlier versions and the area-based self-attention mechanism introduced in YOLOv12 are limited to local information aggregation and pairwise correlation modeling, lacking the capability to capture global multi-to-multi high-order correlations, which limits detection performance in complex scenarios. In this paper, we propose YOLOv13, an accurate and lightweight object detector. To address the above-mentioned challenges, we propose a Hypergraph-based Adaptive Correlation Enhancement (HyperACE) mechanism that adaptively exploits latent high-order correlations and overcomes the limitation of previous methods that are restricted to pairwise correlation modeling based on hypergraph computation, achieving efficient global cross-location and cross-scale feature fusion and enhancement. Subsequently, we propose a Full-Pipeline Aggregation-and-Distribution (FullPAD) paradigm based on HyperACE, which effectively achieves fine-grained information flow and representation synergy within the entire network by distributing correlation-enhanced features to the full pipeline. Finally, we propose to leverage depthwise separable convolutions to replace vanilla large-kernel convolutions, and design a series of blocks that significantly reduce parameters and computational complexity without sacrificing performance. We conduct extensive experiments on the widely used MS COCO benchmark, and the experimental results demonstrate that our method achieves state-of-the-art performance with fewer parameters and FLOPs. Specifically, our YOLOv13-N improves mAP by 3.0% over YOLO11-N and by 1.5% over YOLOv12-N. The code and models of our YOLOv13 model are available at: https://github.com/iMoonLab/yolov13.

Problem

• Enhances global multi-to-multi high-order correlation modeling in object detection
• Overcomes limitations of local information aggregation in YOLO series
• Reduces parameters and computational complexity without sacrificing performance

Innovation

• Hypergraph-based Adaptive Correlation Enhancement mechanism
• Full-Pipeline Aggregation-and-Distribution paradigm
• Depthwise separable convolutions replace vanilla convolutions