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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ciampi, Luca, Azmoudeh, Ali, Akbaba, Elif Ecem, Sarıtaş, Erdi, Yazıcı, Ziya Ata, Ekenel, Hazım Kemal, Amato, Giuseppe, Falchi, Fabrizio
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912889134120960
author Ciampi, Luca
Azmoudeh, Ali
Akbaba, Elif Ecem
Sarıtaş, Erdi
Yazıcı, Ziya Ata
Ekenel, Hazım Kemal
Amato, Giuseppe
Falchi, Fabrizio
author_facet Ciampi, Luca
Azmoudeh, Ali
Akbaba, Elif Ecem
Sarıtaş, Erdi
Yazıcı, Ziya Ata
Ekenel, Hazım Kemal
Amato, Giuseppe
Falchi, Fabrizio
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_19184
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approaches
Ciampi, Luca
Azmoudeh, Ali
Akbaba, Elif Ecem
Sarıtaş, Erdi
Yazıcı, Ziya Ata
Ekenel, Hazım Kemal
Amato, Giuseppe
Falchi, Fabrizio
Computer Vision and Pattern Recognition
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.
title A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approaches
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.19184