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

TL;DR

YOLOv13 introduces a hypergraph-based adaptive correlation mechanism and a full-pipeline aggregation paradigm to enhance global feature fusion, achieving state-of-the-art real-time object detection with fewer parameters.

Contribution

The paper presents YOLOv13, a novel object detector that employs hypergraph-based high-order correlation modeling and a full-pipeline feature aggregation approach for improved detection accuracy.

Findings

Achieves state-of-the-art performance on MS COCO with fewer parameters.

Improves mAP by 3.0% over YOLOv11-N and 1.5% over YOLOv12-N.

Reduces computational complexity using depthwise separable convolutions.

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.