A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approaches

TL;DR

This survey comprehensively reviews class-agnostic counting (CAC) methods, categorizing approaches into reference-based, reference-less, and open-world text-guided paradigms, highlighting recent advancements and challenges in flexible object counting.

Contribution

It provides the first taxonomy of CAC approaches, analyzes 30 architectures, and benchmarks their performance, offering insights into strengths, limitations, and future research directions.

Findings

Reference-based methods achieve top performance.

Open-world text-guided approaches enable flexible class specification.

Benchmark results highlight current challenges in generalization.

Abstract

Visual object counting has recently shifted towards class-agnostic counting (CAC), which addresses the challenge of counting objects across arbitrary categories, a crucial capability for flexible and generalizable counting systems. Unlike humans, who effortlessly identify and count objects from diverse categories without prior knowledge, most existing counting methods are restricted to enumerating instances of known classes, requiring extensive labeled datasets for training and struggling in open-vocabulary settings. In contrast, CAC aims to count objects belonging to classes never seen during training, operating in a few-shot setting. In this paper, we present the first comprehensive review of CAC methodologies. We propose a taxonomy to categorize CAC approaches into three paradigms based on how target object classes can be specified: reference-based, reference-less, and open-world text-guided. Reference-based approaches achieve state-of-the-art performance by relying on exemplar-guided mechanisms. Reference-less methods eliminate exemplar dependency by leveraging inherent image patterns. Finally, open-world text-guided methods use vision-language models, enabling object class descriptions via textual prompts, offering a flexible and promising solution. Based on this taxonomy, we provide an overview of 30 CAC architectures and report their performance on gold-standard benchmarks, discussing key strengths and limitations. Specifically, we present results on the FSC-147 dataset, setting a leaderboard using gold-standard metrics, and on the CARPK dataset to assess generalization capabilities. Finally, we offer a critical discussion of persistent challenges, such as annotation dependency and generalization, alongside future directions.