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

TL;DR

DiagNet introduces a novel object detection method leveraging diagonal constraints on GCN adjacency matrices, eliminating anchor boxes, and demonstrating superior accuracy over YOLO variants on Pascal VOC and MS COCO datasets.

Contribution

It presents a new diagonalization approach for GCNs in object detection, removing the need for anchor boxes and improving detection accuracy.

Findings

Achieves 7.5% higher mAP50 on Pascal VOC than YOLOv1.

Outperforms YOLOv3u, YOLOv5u, and YOLOv8 on MS COCO in mAP.

Introduces two diagonalization algorithms and corresponding loss functions.

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.