DiagNet: Detecting Objects using Diagonal Constraints on Adjacency Matrix of Graph Neural Network

2025/06/04 by Chong Hyun Lee, Lee, Chong Hyun, Kibae Lee +1
Computer Science · #Advanced Graph Neural Networks #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Big Data and Digital Economy #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2506.03571

openalex publication_date 2025/06/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• YOLOv10: Real-Time End-to-End Object Detection
• YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
• Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization\n Uncertainty for Autonomous Driving
• FCOS: Fully Convolutional One-Stage Object Detection
• CornerNet: Detecting Objects as Paired Keypoints
• YOLOv3: An Incremental Improvement
• Mask R-CNN
• YOLO9000: Better, Faster, Stronger
• Semi-Supervised Classification with Graph Convolutional Networks
• Deep Residual Learning for Image Recognition
• You Only Look Once: Unified, Real-Time Object Detection
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Fast R-CNN
• Microsoft COCO: Common Objects in Context
• Rich feature hierarchies for accurate object detection and semantic\n segmentation
• The Graph Neural Network Model

Related

• G-CNN: an Iterative Grid Based Object Detector
• Bermuda Triangles: GNNs Fail to Detect Simple Topological Structures
• OD-GCN: Object Detection Boosted by Knowledge GCN
• Point Linking Network for Object Detection
• Topology and Prediction Focused Research on Graph Convolutional Neural Networks