Exemplar Free Class Agnostic Counting

TL;DR

This paper introduces a fully automated class-agnostic counting method that identifies exemplars within an image and counts objects without test-time adaptation, outperforming previous approaches.

Contribution

It presents a novel fully automated visual counter with a region proposal network for exemplar identification, eliminating the need for test-time adaptation in class-agnostic counting.

Findings

Achieves superior performance on FSC-147 dataset

Operates without test-time adaptation

Uses a novel region proposal network for exemplar detection

Abstract

We tackle the task of Class Agnostic Counting, which aims to count objects in a novel object category at test time without any access to labeled training data for that category. All previous class agnostic counting methods cannot work in a fully automated setting, and require computationally expensive test time adaptation. To address these challenges, we propose a visual counter which operates in a fully automated setting and does not require any test time adaptation. Our proposed approach first identifies exemplars from repeating objects in an image, and then counts the repeating objects. We propose a novel region proposal network for identifying the exemplars. After identifying the exemplars, we obtain the corresponding count by using a density estimation based Visual Counter. We evaluate our proposed approach on FSC-147 dataset, and show that it achieves superior performance compared to the existing approaches.