Dense Center-Direction Regression for Object Counting and Localization with Point Supervision

TL;DR

This paper introduces CeDiRNet, a novel dense regression approach for point-supervised object counting and localization that improves accuracy by using center-direction information and domain-agnostic localization.

Contribution

The paper presents a new dense regression method for point supervision that enhances object localization and counting, with a lightweight network trained independently of the target domain.

Findings

Outperforms state-of-the-art methods on six datasets

Effective domain-agnostic localization network

Improved object counting and localization accuracy

Abstract

Object counting and localization problems are commonly addressed with point supervised learning, which allows the use of less labor-intensive point annotations. However, learning based on point annotations poses challenges due to the high imbalance between the sets of annotated and unannotated pixels, which is often treated with Gaussian smoothing of point annotations and focal loss. However, these approaches still focus on the pixels in the immediate vicinity of the point annotations and exploit the rest of the data only indirectly. In this work, we propose a novel approach termed CeDiRNet for point-supervised learning that uses a dense regression of directions pointing towards the nearest object centers, i.e. center-directions. This provides greater support for each center point arising from many surrounding pixels pointing towards the object center. We propose a formulation of center-directions that allows the problem to be split into the domain-specific dense regression of center-directions and the final localization task based on a small, lightweight, and domain-agnostic localization network that can be trained with synthetic data completely independent of the target domain. We demonstrate the performance of the proposed method on six different datasets for object counting and localization, and show that it outperforms the existing state-of-the-art methods. The code is accessible on GitHub at https://github.com/vicoslab/CeDiRNet.git.