Learning Gaussian Maps for Dense Object Detection

TL;DR

This paper enhances dense object detection by integrating Gaussian maps into RetinaNet, significantly improving accuracy in scenes with many similar objects without increasing computational cost.

Contribution

The paper introduces Gaussian Layer and Gaussian Decoder modules into RetinaNet, achieving state-of-the-art results in dense object detection tasks.

Findings

6% increase in mAP over baseline RetinaNet

Achieves state-of-the-art accuracy on SKU110K dataset

Improves detection in scenes with numerous similar objects

Abstract

Object detection is a famous branch of research in computer vision, many state of the art object detection algorithms have been introduced in the recent past, but how good are those object detectors when it comes to dense object detection? In this paper we review common and highly accurate object detection methods on the scenes where numerous similar looking objects are placed in close proximity with each other. We also show that, multi-task learning of gaussian maps along with classification and bounding box regression gives us a significant boost in accuracy over the baseline. We introduce Gaussian Layer and Gaussian Decoder in the existing RetinaNet network for better accuracy in dense scenes, with the same computational cost as the RetinaNet. We show the gain of 6\% and 5\% in mAP with respect to baseline RetinaNet. Our method also achieves the state of the art accuracy on the SKU110K \cite{sku110k} dataset.