Unsupervised learning of image classes from dynamic video stream
Unsupervised learning of image classes from dynamic video stream
Online Unsupervised Learning of Visual Representations and Categories
arXiv paper abstract https://arxiv.org/abs/2109.05675v1
arXiv PDF paper https://arxiv.org/pdf/2109.05675v1.pdf
Real world learning scenarios involve a nonstationary distribution of classes ... demand learning on-the-fly from few or no class labels.
... propose an unsupervised model that simultaneously performs online visual representation learning and few-shot learning of new categories without relying on any class labels.
... model ... determines when to form a new class prototype. ... formulate ... online Gaussian mixture model
... includes a contrastive loss that encourages different views of the same image to be assigned to the same prototype.
... forms categorical representations of objects in nonstationary environments.
... can learn from an online stream of visual input data and is
significantly better at category recognition compared to state-of-the-art self-supervised learning methods.
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
#ComputerVision #Recognition #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning
Comments