Metraipolis › archive › dc_fd172e6534e3

Smooth bounding box for object detection — arXiv:2611.00676

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00676
License (as archived)
CC0-1.0
Archived
2026-11-03T18:53:13.117Z
SHA-256 of the archived text
01b69cdd30d3919ff9178f46b9b22a5bc18748a16e544efdf476c88b68f13da7
Stable URL of this page
https://metraipolis.com/documento/dc_fd172e6534e3

How to cite

Smooth bounding box for object detection — arXiv:2611.00676 — arXiv (en), https://arxiv.org/abs/2611.00676 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd172e6534e3 (Metraipolis archive dc_fd172e6534e3, sha256 01b69cdd30d3919ff9178f46b9b22a5bc18748a16e544efdf476c88b68f13da7)
BibTeX
@misc{dcfd172e6534e3,
  title = {Smooth bounding box for object detection — arXiv:2611.00676},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00676},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd172e6534e3; sha256 01b69cdd30d3919ff9178f46b9b22a5bc18748a16e544efdf476c88b68f13da7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00676. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep learning-based object detection models are highly dependent on the quality of annotated training data. However, large-scale datasets often contain inevitable label noise, with bounding box localization errors being a prevalent and impactful form in object detection. While label noise handling techniques are well-studied for image classification, their adaptation to the more complex problem of bounding box errors remains underexplored. To address this, we propose a novel Smooth Bounding Box (SBB) strategy to mitigate the adverse effects of bounding box annotation inaccuracies. Our key insight is that annotation errors are often linked to annotator factors rather than specific image content, allowing for a statistical correction approach. Based on object size distribution within datasets, we implement the SBB strategy through two methods: 1) Global Scaling Correction (GSC), which applies a uniform scaling factor to estimate and correct a global average error; and 2) Interval Scaling Correction (ISC), which categorizes objects by size into intervals and estimates a dedicated correction factor for each, enabling more precise, fine-grained calibration. For efficient optimization of multiple parameters in ISC, we design a tailored model fine-tuning strategy. Furthermore, we introduce a Normalized Residual Fluctuation (NRF) metric to quantitatively assess the smoothing effect and training stability. Extensive experiments on multiple benchmarks demonstrate that our method consistently enhances detection accuracy across various model architectures. Both GSC and ISC achieve significant performance improvements over strong baselines, including the latest YOLOv11n, without adding inference overhead. The codes are available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.00676 — 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 2026-11-03T18:16:52.891Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).