US Patent Application 18341050. METHOD AND APPARATUS FOR DATA EFFICIENT SEMANTIC SEGMENTATION simplified abstract
Contents
METHOD AND APPARATUS FOR DATA EFFICIENT SEMANTIC SEGMENTATION
Organization Name
Inventor(s)
Qingfeng Liu of San Diego CA (US)
Mostafa El-khamy of San Diego CA (US)
Jungwon Lee of San Diego CA (US)
Behnam Babagholami Mohamadabadi of San Diego CA (US)
METHOD AND APPARATUS FOR DATA EFFICIENT SEMANTIC SEGMENTATION - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 18341050 Titled 'METHOD AND APPARATUS FOR DATA EFFICIENT SEMANTIC SEGMENTATION'
Simplified Explanation
The abstract describes a method and system for training a neural network. It involves taking an input image and applying data augmentation methods to it, which are selected from a pool of available methods. This generates an augmented image. Additionally, a mixed image is created by combining the original input image with the augmented image.
Original Abstract Submitted
A method and system for training a neural network are provided. The method includes receiving an input image, selecting at least one data augmentation method from a pool of data augmentation methods, generating an augmented image by applying the selected at least one data augmentation method to the input image, and generating a mixed image from the input image and the augmented image.
