Interactive Class-Agnostic Object Counting

TL;DR

This paper introduces an interactive, class-agnostic object counting framework that allows user feedback to iteratively improve counting accuracy, significantly reducing errors with minimal input.

Contribution

It presents a novel interactive framework with a refinement module and adaptation loss, enabling effective correction of counting errors in density-based visual counters.

Findings

Reduces mean absolute error by 30-40% on benchmarks

Works with any density-based visual counter

Requires minimal user feedback for significant improvement

Abstract

We propose a novel framework for interactive class-agnostic object counting, where a human user can interactively provide feedback to improve the accuracy of a counter. Our framework consists of two main components: a user-friendly visualizer to gather feedback and an efficient mechanism to incorporate it. In each iteration, we produce a density map to show the current prediction result, and we segment it into non-overlapping regions with an easily verifiable number of objects. The user can provide feedback by selecting a region with obvious counting errors and specifying the range for the estimated number of objects within it. To improve the counting result, we develop a novel adaptation loss to force the visual counter to output the predicted count within the user-specified range. For effective and efficient adaptation, we propose a refinement module that can be used with any density-based visual counter, and only the parameters in the refinement module will be updated during adaptation. Our experiments on two challenging class-agnostic object counting benchmarks, FSCD-LVIS and FSC-147, show that our method can reduce the mean absolute error of multiple state-of-the-art visual counters by roughly 30% to 40% with minimal user input. Our project can be found at https://yifehuang97.github.io/ICACountProjectPage/.