Papers › Fractal Calibration for long-tailed object detection

Fractal Calibration for long-tailed object detection

15 Oct 2024CVPR 2025 1arXiv:2410.11774archive 2025-07-28

Konstantinos Panagiotis Alexandridis, Ismail Elezi, Jiankang Deng, Anh Nguyen, Shan Luo

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 downweight 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. The code will be released.

PaperPDFConference PDFCode

Code

kostas1515/FRACAL officialmentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Instance SegmentationLong-tailed Object DetectionObjectObject DetectionSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation LVIS v1.0 val FRACAL-Swin-B mask AP 38.5 #10 of 25 Archive leaderboard report
Instance Segmentation LVIS v1.0 val FRACAL-Swin-B mask APr 35.5 #10 of 25 Archive leaderboard report
Instance Segmentation LVIS v1.0 val FRACAL-SwinS mask AP 33.6 #13 of 25 Archive leaderboard report
Instance Segmentation LVIS v1.0 val FRACAL-SwinS mask APr 27.8 #13 of 25 Archive leaderboard report
Instance Segmentation LVIS v1.0 val FRACAL-SwinT mask AP 30.7 #14 of 25 Archive leaderboard report
Instance Segmentation LVIS v1.0 val FRACAL-SwinT mask APr 25.7 #14 of 25 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Focus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections