AdaCount: Training-Free Similarity-Guided Spatial and Feature Adaptation for Zero-Shot Object Counting
Abstract
Zero-shot object counting (ZOC) aims to count instances of arbitrary object categories specified only through textual prompts. Recent training-free approaches leverage foundation models such as SAM to reformulate counting as a prompt-driven segmentation task, eliminating the need for costly counting-specific training data with point-level annotations. More recently, SAM3 introduced promptable concept segmentation, enabling the zero-shot segmentation of all instances corresponding to a text-defined concept. However, SAM3 struggles in densely populated scenes containing numerous small objects, where limited image resolution and insufficient attention to target-relevant regions often lead to missed instances and poor instance separation, hindering accurate object counting. To address this limitation, we propose AdaCount, a training-free framework for ZOC based on similarity-guided spatial and feature adaptation. AdaCount first estimates a prototype-driven similarity map that identifies target-relevant regions. This similarity map subsequently guides two complementary adaptations: (i) similarity-guided spatial warping, which reallocates image resolution toward target instances, and (ii) feature modulation, which amplifies target-relevant encoder representations. Together, these adaptations enable SAM3 to devote greater representational capacity to target-relevant regions while preserving global image context, without requiring any model retraining. Extensive experiments across six diverse counting benchmarks establish AdaCount as a new SOTA among training-free ZOC approaches.
Method
Overview of AdaCount. Given an input image and text query, AdaCount first performs an initial SAM3 pass to discover high-confidence target exemplars. These exemplars are used to construct image-specific prototypes that guide similarity estimation, spatial adaptation, and feature modulation before a second SAM3 inference pass produces the final object count.
Results
BibTeX
@article{Siddiqui2026Adacount,
title={AdaCount: Training-Free Similarity-Guided Spatial and Feature Adaptation for
Zero-Shot Object Counting},
author={Muhammad Ibraheem Siddiqui, Muhammad Haris Khan},
journal={arXiv},
year={2026},
}