Where are the Blobs: Counting by Localization with Point Supervision

TL;DR

This paper introduces a detection-based object counting method that uses point supervision and a novel loss function, outperforming regression-based approaches and even some methods with stronger supervision.

Contribution

A new detection-based counting approach with a point-supervision loss, effective blob splitting, and state-of-the-art results on multiple datasets.

Findings

Outperforms regression-based counting methods.

Achieves state-of-the-art results on Pascal VOC and Penguins datasets.

Requires only point annotations, reducing annotation complexity.

Abstract

Object counting is an important task in computer vision due to its growing demand in applications such as surveillance, traffic monitoring, and counting everyday objects. State-of-the-art methods use regression-based optimization where they explicitly learn to count the objects of interest. These often perform better than detection-based methods that need to learn the more difficult task of predicting the location, size, and shape of each object. However, we propose a detection-based method that does not need to estimate the size and shape of the objects and that outperforms regression-based methods. Our contributions are three-fold: (1) we propose a novel loss function that encourages the network to output a single blob per object instance using point-level annotations only; (2) we design two methods for splitting large predicted blobs between object instances; and (3) we show that our method achieves new state-of-the-art results on several challenging datasets including the Pascal VOC and the Penguins dataset. Our method even outperforms those that use stronger supervision such as depth features, multi-point annotations, and bounding-box labels.