Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: D'Alessandro, Adriano, Mahdavi-Amiri, Ali, Hamarneh, Ghassan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2504.11705
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908729205587968
author D'Alessandro, Adriano
Mahdavi-Amiri, Ali
Hamarneh, Ghassan
author_facet D'Alessandro, Adriano
Mahdavi-Amiri, Ali
Hamarneh, Ghassan
contents Class-agnostic counting (CAC) methods reduce annotation costs by letting users define what to count at test-time through text or visual exemplars. However, current open-vocabulary approaches work well for broad categories but fail when fine-grained category distinctions are needed, such as telling apart waterfowl species or pepper cultivars. We present FiGO, a new annotation-free method that adapts existing counting models to fine-grained categories using only the category name. Our approach uses a text-to-image diffusion model to create synthetic examples and a joint positive/hard-negative loss to learn a compact concept embedding that conditions a specialization module to convert outputs from any frozen counter into accurate, fine-grained estimates. To evaluate fine-grained counting, we introduce LOOKALIKES, a dataset of 37 subcategories across 14 parent categories with many visually similar objects per image. Our method substantially outperforms strong open-vocabulary baselines, moving counting systems from "count all the peppers" to "count only the habaneros."
format Preprint
id arxiv_https___arxiv_org_abs_2504_11705
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FiGO: Fine-Grained Object Counting without Annotations
D'Alessandro, Adriano
Mahdavi-Amiri, Ali
Hamarneh, Ghassan
Computer Vision and Pattern Recognition
Class-agnostic counting (CAC) methods reduce annotation costs by letting users define what to count at test-time through text or visual exemplars. However, current open-vocabulary approaches work well for broad categories but fail when fine-grained category distinctions are needed, such as telling apart waterfowl species or pepper cultivars. We present FiGO, a new annotation-free method that adapts existing counting models to fine-grained categories using only the category name. Our approach uses a text-to-image diffusion model to create synthetic examples and a joint positive/hard-negative loss to learn a compact concept embedding that conditions a specialization module to convert outputs from any frozen counter into accurate, fine-grained estimates. To evaluate fine-grained counting, we introduce LOOKALIKES, a dataset of 37 subcategories across 14 parent categories with many visually similar objects per image. Our method substantially outperforms strong open-vocabulary baselines, moving counting systems from "count all the peppers" to "count only the habaneros."
title FiGO: Fine-Grained Object Counting without Annotations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.11705