Fractal Calibration for long-tailed object detection
File(s)
Accepted version
Author(s)
Alexandridis, Konstantinos Panagiotis
Elezi, Ismail
Deng, Jiankang
Nguyen, Anh
Luo, Shan
Type
Conference Paper
Abstract
Real-world datasets follow an imbalanced distribution, which poses significant challenges in rare-category object detection. Recent studies tackle this problem by developing re-weighting and re-sampling methods, that utilise the class frequencies of the dataset. However, these techniques focus solely on the frequency statistics and ignore the distribution of the classes in image space, missing important information. In contrast to them, we propose FRActal CALibration (FRACAL): a novel post-calibration method for long-tailed object detection. FRACAL devises a logit adjustment method that utilises the fractal dimension to estimate how uniformly classes are distributed in image space. During inference, it uses the fractal dimension to inversely down-weight the probabilities of uniformly spaced class predictions achieving balance in two axes: between frequent and rare categories, and between uniformly spaced and sparsely spaced classes. FRACAL is a post-processing method and it does not require any training, also it can be combined with many off-the-shelf models such as one-stage sigmoid detectors and two-stage instance segmentation models. FRACAL boosts the rare class performance by up to 8.6% and surpasses all previous methods on LVIS dataset, while showing good generalisation to other datasets such as COCO, V3Det and OpenImages. We provide the code at https://github.com/kostas1515/FRACAL.
Date Issued
2025-08-13
Date Acceptance
2025-06-01
Citation
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, pp.15139-15150
ISSN
1063-6919
Publisher
IEEE
Start Page
15139
End Page
15150
Journal / Book Title
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Copyright Statement
Copyright © 2025, IEEE. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Source
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publication Status
Published
Start Date
2025-06-10
Finish Date
2025-06-17
Coverage Spatial
Nashville, TN, USA