Small object detection using bounding boxes guided by confidences with C-BBL
Small object detection using bounding boxes guided by confidences with C-BBL
Confidence-driven Bounding Box Localization for Small Object Detection
arXiv paper abstract https://arxiv.org/abs/2303.01803
arXiv PDF paper https://arxiv.org/pdf/2303.01803.pdf
Despite advancements in generic object detection, there remains a performance gap in detecting small objects compared to normal-scale objects.
... observe that existing bounding box regression methods tend to produce distorted gradients for small objects and result in less accurate localization.
... present a novel Confidence-driven Bounding Box Localization (C-BBL) method to rectify the gradients. C-BBL quantizes continuous labels into grids and formulates two-hot ground truth labels.
In prediction, the bounding box head generates a confidence distribution over the grids.
Unlike the bounding box regression paradigms in conventional detectors, ... introduce a classification-based localization objective through cross entropy between ground truth and predicted confidence distribution, generating confidence-driven gradients.
... The method is evaluated on multiple detectors using three object detection benchmarks and consistently improves baseline detectors, achieving state-of-the-art performance ...
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
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
#ComputerVision #ObjectDetection #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning
Comments