Training Multi-Object Detector by Estimating Bounding Box Distribution for Input Image

TL;DR

This paper introduces MDOD, a novel neural network that models bounding boxes as a probability density, simplifying training and improving multi-object detection performance on datasets like MS COCO.

Contribution

The paper presents a new density estimation approach for multi-object detection, replacing heuristic assignment with a mixture model-based training method.

Findings

Improved detection accuracy on MS COCO dataset.

Effective handling of variable numbers of objects per image.

Simplified training process compared to traditional methods.

Abstract

In multi-object detection using neural networks, the fundamental problem is, "How should the network learn a variable number of bounding boxes in different input images?". Previous methods train a multi-object detection network through a procedure that directly assigns the ground truth bounding boxes to the specific locations of the network's output. However, this procedure makes the training of a multi-object detection network too heuristic and complicated. In this paper, we reformulate the multi-object detection task as a problem of density estimation of bounding boxes. Instead of assigning each ground truth to specific locations of network's output, we train a network by estimating the probability density of bounding boxes in an input image using a mixture model. For this purpose, we propose a novel network for object detection called Mixture Density Object Detector (MDOD), and the corresponding objective function for the density-estimation-based training. We applied MDOD to MS COCO dataset. Our proposed method not only deals with multi-object detection problems in a new approach, but also improves detection performances through MDOD. The code is available: https://github.com/yoojy31/MDOD.