Get out-of-distribution objects by observe they fall outside boxes for in-distribution data with BAM
Get out-of-distribution objects by observe they fall outside boxes for in-distribution data with BAM
BAM: Box Abstraction Monitors for Real-time OoD Detection in Object Detection
arXiv paper abstract https://arxiv.org/abs/2403.18373
arXiv PDF paper https://arxiv.org/pdf/2403.18373.pdf
Out-of-distribution (OoD) detection techniques for deep neural networks (DNNs) become crucial thanks to their filtering of abnormal inputs
... Nevertheless, integrating OoD detection into state-of-the-art (SOTA) object detection DNNs poses significant challenges
... proposes a simple ... method that requires neither retraining nor architectural change in object detection DNN, called Box Abstraction-based Monitors (BAM).
... using a finite union of convex box abstractions to capture the learned features of objects for in-distribution (ID) data, and an important observation that features from OoD data are more likely to fall outside of these boxes.
The union of convex regions within the feature space allows the formation of non-convex and interpretable decision boundaries, overcoming the limitations of VOS-like detectors without sacrificing real-time performance.
... integrating BAM into Faster R-CNN-based object detection DNNs demonstrate a considerably improved performance against SOTA OoD detection techniques.
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