Papers › T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting

T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting

1 Jan 2025CVPR 2025 1archive 2025-07-28

Yifei Qian, Zhongliang Guo, Bowen Deng, Chun Tong Lei, Shuai Zhao, Chun Pong Lau, Xiaopeng Hong, Michael P. Pound

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

PaperPDFCode

Code

cha15yq/t2icount officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DenoisingObject CountingSensitivityZero-Shot Counting

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIPConcatenated Skip ConnectionConvolutionDiffusionFocusMax PoolingReLUU-Net

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections