End-to-End Multi-Object Detection with a Regularized Mixture Model

TL;DR

This paper introduces D-RMM, an end-to-end multi-object detection framework that models detection as density estimation with a regularized mixture model, reducing heuristics and improving confidence score reliability.

Contribution

The paper proposes a novel training framework for end-to-end multi-object detection using a regularized mixture density model, eliminating reliance on heuristics like NMS.

Findings

Outperforms previous end-to-end detectors on MS COCO

Reduces heuristics in training process

Improves confidence score reliability

Abstract

Recent end-to-end multi-object detectors simplify the inference pipeline by removing hand-crafted processes such as non-maximum suppression (NMS). However, during training, they still heavily rely on heuristics and hand-crafted processes which deteriorate the reliability of the predicted confidence score. In this paper, we propose a novel framework to train an end-to-end multi-object detector consisting of only two terms: negative log-likelihood (NLL) and a regularization term. In doing so, the multi-object detection problem is treated as density estimation of the ground truth bounding boxes utilizing a regularized mixture density model. The proposed \textit{end-to-end multi-object Detection with a Regularized Mixture Model} (D-RMM) is trained by minimizing the NLL with the proposed regularization term, maximum component maximization (MCM) loss, preventing duplicate predictions. Our method reduces the heuristics of the training process and improves the reliability of the predicted confidence score. Moreover, our D-RMM outperforms the previous end-to-end detectors on MS COCO dataset.