arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.20153cs.CV
收藏

CoDi——一种用于少样本计数的示例条件扩散模型

CoDi -- an exemplar-conditioned diffusion model for low-shot counting

Faculty of Computer and Information Science, University of Ljubljana(计算机与信息科学学院,卢布尔雅那大学)

Grega Šuštar, Jer Pelhan, Alan Lukežič, Matej Kristan

AI总结:

研究少样本目标计数问题,提出基于潜在扩散的CoDi模型,其核心是基于示例的条件模块,能生成高质量密度图。在FSC和MCAC基准测试中表现出色,分别在少样本等场景及整体上大幅超越现有技术。

摘要:

少样本目标计数旨在仅使用少量或无标注的测试时示例来估计图像中先前未观察到的目标数量。现代少样本计数器面临的一个重大挑战是存在小目标的密集区域。基于密度的计数器通常能很好地处理此类情况下的总数,但定位能力较差。基于点检测的计数器定位能力较好,但由于预训练查询数量有限,在目标数量非常多的图像上表现不佳。我们提出了CoDi,首个基于潜在扩散的少样本计数器,能生成高质量密度图。核心贡献是新的基于示例的条件模块,可提取并调整目标原型到去噪网络中间层。在FSC基准测试中,CoDi在少样本、单样本和无参考场景下分别比现有技术高出15% MAE、13% MAE和10% MAE,在MCAC基准测试中比顶级方法高出38% MAE,创造了新的技术水平。代码可通过此https URL获取。

英文摘要:

Low-shot object counting addresses estimating the number of previously unobserved objects in an image using only few or no annotated test-time exemplars. A considerable challenge for modern low-shot counters are dense regions with small objects. While total counts in such situations are typically well addressed by density-based counters, their usefulness is limited by poor localization capabilities. This is better addressed by point-detection-based counters, which are based on query-based detectors. However, due to limited number of pre-trained queries, they underperform on images with very large numbers of objects, and resort to ad-hoc techniques like upsampling and tiling. We propose CoDi, the first latent diffusion-based low-shot counter that produces high-quality density maps on which object locations can be determined by non-maxima suppression. Our core contribution is the new exemplar-based conditioning module that extracts and adjusts the object prototypes to the intermediate layers of the denoising network, leading to accurate object location estimation. On FSC benchmark, CoDi outperforms state-of-the-art by 15% MAE, 13% MAE and 10% MAE in the few-shot, one-shot, and reference-less scenarios, respectively, and sets a new state-of-the-art on MCAC benchmark by outperforming the top method by 38% MAE. The code is available at https://github.com/gsustar/CoDi

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑