{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/t2icount-enhancing-cross-modal-understanding","title":"T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting","arxiv_id":null,"date":"2025-01-01","proceeding":"CVPR 2025 1","authors":["Yifei Qian","Zhongliang Guo","Bowen Deng","Chun Tong Lei","Shuai Zhao","Chun Pong Lau","Xiaopeng Hong","Michael P. Pound"],"abstract":"    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 denoising 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    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2025/html/Qian_T2ICount_Enhancing_Cross-modal_Understanding_for_Zero-Shot_Counting_CVPR_2025_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2025/papers/Qian_T2ICount_Enhancing_Cross-modal_Understanding_for_Zero-Shot_Counting_CVPR_2025_paper.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"t2icount-enhancing-cross-modal-understanding","repo_url":"https://github.com/cha15yq/t2icount","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"object-counting","task_name":"Object Counting"},{"task_slug":"sensitivity","task_name":"Sensitivity"},{"task_slug":"zero-shot-counting","task_name":"Zero-Shot Counting"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}