SAIOU: A SYNERGISTIC ADAPTIVE IOU LOSS FOR BOUNDARY BOX REGRESSION
Bounding Box Regression (BBR) is a critical component of modern object detectors, with its performance heavily dependent on the loss function design. However, existing IoU-based losses exhibit significant shortcomings in synergistically optimizing for
Authors
- Zhen Tian (ORCID: https://orcid.org/0000-0003-4093-8469)
- Xu Wang (ORCID: https://orcid.org/0000-0001-5551-0815)
- Puyu Han (ORCID: https://orcid.org/0000-0002-0380-7462)
- Luqi Gong (ORCID: https://orcid.org/0009-0000-8744-8630)
- Zicheng Lin
- Weichao Pan (ORCID: https://orcid.org/0009-0009-3303-397X)
Institutions
- Zhejiang Lab (CN)
- Shandong Jianzhu University (CN)
- University of Glasgow (GB)
Publication Details
- Published
- 2025-09-25
- DOI
- https://doi.org/10.36227/techrxiv.175877882.27888159/v1
- Primary Topic
- Anomaly Detection Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00