Survey of training object detectors with limited data or unlabeled data
Survey of training object detectors with limited data or unlabeled data
A Survey of Self-Supervised and Few-Shot Object Detection
arXiv paper abstract https://arxiv.org/abs/2110.14711v1
arXiv PDF paper https://arxiv.org/pdf/2110.14711v1.pdf
Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation
… few-shot object detection is about training a model on novel (unseen) object classes with little data … requires prior training on many labeled examples of base (seen) classes.
… self-supervised methods aim at learning representations from unlabeled data which transfer well to … object detection.
Combining few-shot and self-supervised object detection is a promising research direction.
… review and characterize the most recent approaches on few-shot and self-supervised object detection. …
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
