US Patent Application 17729878. NOVEL CATEGORY DISCOVERY USING MACHINE LEARNING simplified abstract
Contents
NOVEL CATEGORY DISCOVERY USING MACHINE LEARNING
Organization Name
Inventor(s)
NOVEL CATEGORY DISCOVERY USING MACHINE LEARNING - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 17729878 Titled 'NOVEL CATEGORY DISCOVERY USING MACHINE LEARNING'
Simplified Explanation
This abstract describes a method for discovering new categories using computer programs. The method involves generating local feature tensors from training images and comparing them to previous feature tensors. A similarity tensor is created to represent the similarity between the current and previous feature tensors. A neural network is used to process the training images and predict their classes. The similarity between the feature tensors and the training outputs is used to update the neural network.
Original Abstract Submitted
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing novel category discovery. One of the methods includes generating first local feature tensors from a first training image; obtaining previous local feature tensors generated from a previous training image; generating a first similarity tensor representing a similarity between the first local feature tensors and the previous local feature tensors; obtaining a second similarity tensor for a second training image; processing, using a neural network, the first training image to generate a first training output representing a class prediction for the first training image; obtaining a second training output representing a class prediction for the second training image; and generating an update to the neural network from (i) a similarity between the first similarity tensor and the second similarity tensor and (ii) a similarity between the first training output and the second training output.
