Metraipolis › archive › dc_4b4bd3e4a2ef
Counting Beyond Instances: A Benchmark for Group-Individual Object Counting — arXiv:2609.04716
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.04716
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T23:33:27.584Z
- SHA-256 of the archived text
71ca311eb9e1fe393e25d7f6dec995fb81dda4c1e250b15248d3a7c5a18f18d1- Stable URL of this page
https://metraipolis.com/documento/dc_4b4bd3e4a2ef
How to cite
Counting Beyond Instances: A Benchmark for Group-Individual Object Counting — arXiv:2609.04716 — arXiv (en), https://arxiv.org/abs/2609.04716 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4b4bd3e4a2ef (Metraipolis archive dc_4b4bd3e4a2ef, sha256 71ca311eb9e1fe393e25d7f6dec995fb81dda4c1e250b15248d3a7c5a18f18d1)
BibTeX
@misc{dc4b4bd3e4a2ef,
title = {Counting Beyond Instances: A Benchmark for Group-Individual Object Counting — arXiv:2609.04716},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.04716},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4b4bd3e4a2ef; sha256 71ca311eb9e1fe393e25d7f6dec995fb81dda4c1e250b15248d3a7c5a18f18d1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04716. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Visual counting is commonly formulated at the instance level, aiming to estimate how many objects of a queried category appear in an image. However, real-world counting often involves higher-level semantic units formed by multiple instances, such as a bunch of grapes, a stack of plates, or a pair of shoes. This exposes a key limitation of existing counting formulations, which mainly focus on what to count, while largely overlooking at which semantic unit to count. We introduce Group-Individual Object Counting (GIC), a new setting that requires models to count both individual objects and semantic groups within a unified framework. To support this new task, we present BunchCount, a real-world benchmark with 1,330 images, 89,254 individual annotations, and 11,065 group annotations. BunchCount provides paired individual-group annotations within the same image and explicitly records containment relations between each group and its constituent individuals. Experiments on BunchCount show that current advanced counting models perform well on individual instances but fail to count semantic groups more accurately. To mitigate semantic granularity conflict, we propose a counting-unit guided relational counting framework, which exploits group-individual containment relations to regularize cross-granularity representations during training. Our method substantially improves group-level counting while better preserving individual-level counting ability, establishing a strong baseline for counting beyond instances. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.04716 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T23:16:11.397Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).