Detect known and unknown objects with semi-supervised learning by auto-encoder ensemble with OWSSD
Detect known and unknown objects with semi-supervised learning by auto-encoder ensemble with OWSSD
Semi-Supervised Object Detection in the Open World
arXiv paper abstract https://arxiv.org/abs/2307.15710
arXiv PDF paper https://arxiv.org/pdf/2307.15710.pdf
Existing approaches for semi-supervised object detection assume a fixed set of classes present in training and unlabeled datasets, i.e., in-distribution (ID) data.
... these techniques significantly degrades when these techniques are deployed in the open-world, due to the fact that the unlabeled and test data may contain objects that were not seen during training, i.e., out-of-distribution (OOD) data.
... propose the Open World Semi-supervised Detection framework (OWSSD) that effectively detects OOD data along with a semi-supervised learning pipeline that learns from both ID and OOD data.
... introduce an ensemble based OOD detector consisting of lightweight auto-encoder networks trained only on ID data.
... demonstrate that ... method performs competitively against state-of-the-art OOD detection algorithms and also significantly boosts the semi-supervised learning performance in open-world scenarios.
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
Comentarios