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 at https://github.com/cha15yq/T2ICount.

翻译：零样本物体计数旨在通过文本描述计数任意物体类别的实例。现有方法通常依赖如CLIP等视觉-语言模型，但往往对文本提示的敏感性有限。我们提出了T2ICount，一种基于扩散的框架，利用预训练扩散模型中的丰富先验知识和细粒度视觉理解。虽然一步去噪确保了效率，但会导致文本敏感性减弱。为应对这一挑战，我们提出了一个分层语义校正模块，逐步优化文本-图像特征对齐；以及一个表征区域一致性损失，通过利用从去噪U-Net中提取的交叉注意力图来提供可靠的监督信号。此外，我们观察到当前基准测试主要关注图像中的主要物体，可能掩盖模型对文本的敏感性。为此，我们贡献了一个具有挑战性的FSC147重新标注子集，以更好地评估文本引导的计数能力。大量实验表明，我们的方法在不同基准测试中均取得了优越性能。代码可在https://github.com/cha15yq/T2ICount获取。