Metraipolis › archive › dc_c0d38ed1e166
Information Density Imbalance in Visual Object Detection — arXiv:2609.02369
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02369
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:50:03.057Z
- SHA-256 of the archived text
788bf49f0a6b5f5d5a1ce0bd90f34362e48844991b80c19b1d5f360f878aed39- Stable URL of this page
https://metraipolis.com/documento/dc_c0d38ed1e166
How to cite
Information Density Imbalance in Visual Object Detection — arXiv:2609.02369 — arXiv (en), https://arxiv.org/abs/2609.02369 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c0d38ed1e166 (Metraipolis archive dc_c0d38ed1e166, sha256 788bf49f0a6b5f5d5a1ce0bd90f34362e48844991b80c19b1d5f360f878aed39)
BibTeX
@misc{dcc0d38ed1e166,
title = {Information Density Imbalance in Visual Object Detection — arXiv:2609.02369},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02369},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c0d38ed1e166; sha256 788bf49f0a6b5f5d5a1ce0bd90f34362e48844991b80c19b1d5f360f878aed39},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02369. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In object detection, the number of instances is typically used to determine whether a dataset exhibits a long-tailed distribution, implicitly assuming that the model will perform poorly on categories with fewer instances. This assumption has led to extensive research on category bias in datasets with imbalanced instance numbers. However, even in datasets where instance numbers are relatively balanced, models still exhibit category bias, indicating that instance count alone cannot explain this phenomenon. In this work, we first introduce the concept and measurement of information density. We then observe a significant negative correlation between a category's information density and its accuracy, and we investigate how the training process impacts this relationship. Empirical studies suggest that information density imbalance may be a potential source of category bias. To preliminarily validate the potential of information density, we made simple improvements to three advanced object detection loss functions using this concept. Experiments on the Pascal VOC, COCO-LT, and LVIS datasets demonstrate that information density can significantly reduce model bias while effectively enhancing the overall performance of existing loss functions. This study provides a new perspective for understanding the generalized bias phenomenon in object detection models and offers new tools for designing fairer loss functions and training strategies. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.02369 — 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 2026-10-17T05:25:58.109Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).