Object Counting and Instance Segmentation with Image-level Supervision

TL;DR

This paper introduces a novel image-level supervised method for object counting and instance segmentation that estimates density maps and reduces supervision needs, outperforming existing approaches on standard datasets.

Contribution

It is the first to propose density map estimation for object counting and instance segmentation using only image-level supervision with limited object count info.

Findings

Outperforms existing methods on PASCAL VOC and COCO for counting.

Improves state-of-the-art in image-level supervised instance segmentation by 17.8%.

Effectively estimates object density maps with minimal supervision.

Abstract

Common object counting in a natural scene is a challenging problem in computer vision with numerous real-world applications. Existing image-level supervised common object counting approaches only predict the global object count and rely on additional instance-level supervision to also determine object locations. We propose an image-level supervised approach that provides both the global object count and the spatial distribution of object instances by constructing an object category density map. Motivated by psychological studies, we further reduce image-level supervision using a limited object count information (up to four). To the best of our knowledge, we are the first to propose image-level supervised density map estimation for common object counting and demonstrate its effectiveness in image-level supervised instance segmentation. Comprehensive experiments are performed on the PASCAL VOC and COCO datasets. Our approach outperforms existing methods, including those using instance-level supervision, on both datasets for common object counting. Moreover, our approach improves state-of-the-art image-level supervised instance segmentation with a relative gain of 17.8% in terms of average best overlap, on the PASCAL VOC 2012 dataset. Code link: https://github.com/GuoleiSun/CountSeg