AFreeCA: Annotation-Free Counting for All

TL;DR

This paper introduces AFreeCA, an unsupervised method for object counting that leverages text-to-image latent diffusion models to generate counting data without manual annotations, enabling versatile counting across diverse object categories.

Contribution

The paper proposes a novel unsupervised counting approach using LDMs for data generation and density classification, removing the need for annotated datasets and broadening object category applicability.

Findings

Outperforms other unsupervised and few-shot counting methods

Enables counting of diverse object categories without annotations

Uses LDMs to generate reliable counting data

Abstract

Object counting methods typically rely on manually annotated datasets. The cost of creating such datasets has restricted the versatility of these networks to count objects from specific classes (such as humans or penguins), and counting objects from diverse categories remains a challenge. The availability of robust text-to-image latent diffusion models (LDMs) raises the question of whether these models can be utilized to generate counting datasets. However, LDMs struggle to create images with an exact number of objects based solely on text prompts but they can be used to offer a dependable \textit{sorting} signal by adding and removing objects within an image. Leveraging this data, we initially introduce an unsupervised sorting methodology to learn object-related features that are subsequently refined and anchored for counting purposes using counting data generated by LDMs. Further, we present a density classifier-guided method for dividing an image into patches containing objects that can be reliably counted. Consequently, we can generate counting data for any type of object and count them in an unsupervised manner. Our approach outperforms other unsupervised and few-shot alternatives and is not restricted to specific object classes for which counting data is available. Code to be released upon acceptance.