Object detection with noisy bounding boxes using the aggregate region of the proposals with DISCO
Object detection with noisy bounding boxes using the aggregate region of the proposals with DISCO
Distribution-Aware Calibration for Object Detection with Noisy Bounding Boxes
arXiv paper abstract https://arxiv.org/abs/2308.12017
arXiv PDF paper https://arxiv.org/pdf/2308.12017.pdf
Large-scale well-annotated datasets are of great importance for training an effective object detector.
... obtaining accurate bounding box annotations is laborious and demanding ... the resultant noisy bounding boxes ... diminish detection
... ground-truth is usually situated in the aggregation region of the proposals assigned to a noisy ground-truth ... propose DIStribution-aware CalibratiOn (DISCO) to model the spatial distribution of proposals for calibrating supervision signals.
In DISCO, spatial distribution modeling is performed to statistically extract the potential locations of objects.
Based on the modeled distribution ... distribution-aware proposal augmentation (DA-Aug), distribution-aware box refinement (DA-Ref), and distribution-aware confidence estimation (DA-Est), are developed to improve classification, localization, and interpretability, respectively.
... demonstrate that DISCO can achieve state-of-the-art detection performance, especially at high noise levels.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments