Invention Grant
- Patent Title: Segmentation using an unsupervised neural network training technique
-
Application No.: US16378464Application Date: 2019-04-08
-
Publication No.: US11748887B2Publication Date: 2023-09-05
- Inventor: Varun Jampani , Wei-Chih Hung , Sifei Liu , Pavlo Molchanov , Jan Kautz
- Applicant: NVIDIA Corporation
- Applicant Address: US CA Santa Clara
- Assignee: NVIDIA Corporation
- Current Assignee: NVIDIA Corporation
- Current Assignee Address: US CA Santa Clara
- Agency: Davis Wright Tremaine LLP
- Main IPC: G06V10/00
- IPC: G06V10/00 ; G06T7/11 ; G06T7/143 ; G06F17/15 ; G06N3/088 ; G06F18/40 ; G06N3/045 ; G06N3/047 ; G06V10/764 ; G06V10/82 ; G06V10/94 ; G06V20/40
Abstract:
Systems and methods to detect one or more segments of one or more objects within one or more images based, at least in part, on a neural network trained in an unsupervised manner to infer the one or more segments. Systems and methods to help train one or more neural networks to detect one or more segments of one or more objects within one or more images in an unsupervised manner.
Public/Granted literature
- US20200320401A1 SEGMENTATION USING AN UNSUPERVISED NEURAL NETWORK TRAINING TECHNIQUE Public/Granted day:2020-10-08
Information query
