用图神经网络的对角约束实现无需锚框的物体检测
DiagNet: Detecting Objects using Diagonal Constraints on Adjacency Matrix of Graph Neural Network
- 通过硬/软约束对邻接矩阵施加对角化，替代传统锚框设计
- 在Pascal VOC上比YOLOv1高7.5% mAP50，MS COCO上优于多个YOLO版本
- 适合追求无锚框检测与图结构建模的研究者
我们提出DiagNet，一种基于图卷积网络邻接矩阵对角约束的新型物体检测方法。通过硬约束和软约束两种对角化算法，结合对角约束与互补约束的损失函数，实现不依赖锚框的检测。为验证可行性，采用YOLO模型的检测头。实验表明，DiagNet在Pascal VOC上比YOLOv1高出7.5% mAP50；在MS COCO上分别比YOLOv3u、YOLOv5u、YOLOv8高出5.1%、3.7%、2.9% mAP。
原文摘要 · Abstract (English)
We propose DaigNet, a new approach to object detection with which we can detect an object bounding box using diagonal constraints on adjacency matrix of a graph convolutional network (GCN). We propose two diagonalization algorithms based on hard and soft constraints on adjacency matrix and two loss functions using diagonal constraint and complementary constraint. The DaigNet eliminates the need for designing a set of anchor boxes commonly used. To prove feasibility of our novel detector, we adopt detection head in YOLO models. Experiments show that the DiagNet achieves 7.5% higher mAP50 on Pascal VOC than YOLOv1. The DiagNet also shows 5.1% higher mAP on MS COCO than YOLOv3u, 3.7% higher mAP than YOLOv5u, and 2.9% higher mAP than YOLOv8.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。