Back to results
US 11,687,780 B2Granted
Method and apparatus for data efficient semantic segmentation
AssigneeSamsung Electronics Co., Ltd.
InventorsQingfeng Liu, Mostafa El-Khamy, Jungwon Lee, Behnam Babagholami Mohamadabadi
Life of this patent
Estimating the term…
Abstract
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.
Claims18
A method comprising
- receiving input images;
- linearly combining the input images to create mixup images;
- selecting at least one data augmentation method from a pool of data augmentation methods;
- generating respective augmented images for the input images by applying the selected at least one data augmentation method to each of the input images;
- generating mixed images from the input images and the respective augmented images;
- and
- classifying the input images based on the mixup images and the mixed images.
4 more elements
A system comprising:
- a memory;
- and
- a processor configured to:
- receive input images;
- linearly combine the input images to create mixup images;
- select at least one data augmentation method from a pool of data augmentation methods;
- generate respective augmented images for the input images by applying the selected at least one data augmentation method to each of the input images;
- generate mixed images from the input images and the respective augmented images;
- and
- classify the input images based on the mixup images and the mixed images.
7 more elements
Dependencies are inferred from the claim text.