{"ID":2825734,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.20153","arxiv_id":"2512.20153","title":"CoDi -- an exemplar-conditioned diffusion model for low-shot counting","abstract":"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 44% MAE. The code is available at https://github.com/gsustar/CoDi.","short_abstract":"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 dens...","url_abs":"https://arxiv.org/abs/2512.20153","url_pdf":"https://arxiv.org/pdf/2512.20153v1","authors":"[\"Grega Šuštar\",\"Jer Pelhan\",\"Alan Lukežič\",\"Matej Kristan\"]","published":"2025-12-23T08:31:36Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":605692,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2825734,"paper_url":"https://arxiv.org/abs/2512.20153","paper_title":"CoDi -- an exemplar-conditioned diffusion model for low-shot counting","repo_url":"https://github.com/gsustar/CoDi","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}