Zero-shot object counting aims to count instances of arbitrary object categories specified by text descriptions. Existing methods typically rely on vision-language models like CLIP, but often exhibit limited sensitivity to text prompts. We present T2ICount, a diffusion-based framework that leverages rich prior knowledge and fine-grained visual understanding from pretrained diffusion models. While one-step denoising ensures efficiency, it leads to weakened text sensitivity. To address this challenge, we propose a Hierarchical Semantic Correction Module that progressively refines text-image feature alignment, and a Representational Regional Coherence Loss that provides reliable supervision signals by leveraging the cross-attention maps extracted from the denosing U-Net. Furthermore, we observe that current benchmarks mainly focus on majority objects in images, potentially masking models' text sensitivity. To address this, we contribute a challenging re-annotated subset of FSC147 for better evaluation of text-guided counting ability. Extensive experiments demonstrate that our method achieves superior performance across different benchmarks. Code is available atthis https URL.
View on arXiv@article{qian2025_2502.20625,
title={ T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting },
author={ Yifei Qian and Zhongliang Guo and Bowen Deng and Chun Tong Lei and Shuai Zhao and Chun Pong Lau and Xiaopeng Hong and Michael P. Pound },
journal={arXiv preprint arXiv:2502.20625},
year={ 2025 }
}