FocalCount: Towards Class-Count Imbalance in Class-Agnostic Counting

TL;DR

FocalCount introduces a novel method for class-agnostic object counting that addresses class imbalance by estimating category counts and employing a new loss function, improving accuracy in diverse scenarios.

Contribution

It proposes FocalCount, which uses feature attributes for class-count estimation and introduces Focal-MSE loss to enhance sensitivity to underrepresented categories.

Findings

Improves class-specific counting accuracy

Enhances performance in few-shot and zero-shot scenarios

Outperforms existing methods on multiple datasets

Abstract

In class-agnostic object counting, the goal is to estimate the total number of object instances in an image without distinguishing between specific categories. Existing methods often predict this count without considering class-specific outputs, leading to inaccuracies when such outputs are required. These inaccuracies stem from two key challenges: 1) the prevalence of single-category images in datasets, which leads models to generalize specific categories as representative of all objects, and 2) the use of mean squared error loss during training, which applies uniform penalization. This uniform penalty disregards errors in less frequent categories, particularly when these errors contribute minimally to the overall loss. To address these issues, we propose {FocalCount}, a novel approach that leverages diverse feature attributes to estimate the number of object categories in an image. This estimate serves as a weighted factor to correct class-count imbalances. Additionally, we introduce {Focal-MSE}, a new loss function that integrates binary cross-entropy to generate stronger error gradients, enhancing the model's sensitivity to errors in underrepresented categories. Our approach significantly improves the model's ability to distinguish between specific classes and general counts, demonstrating superior performance and scalability in both few-shot and zero-shot scenarios across three object counting datasets. The code will be released soon.