Invention Grant
- Patent Title: Variable bit rate compression using neural network models
-
Application No.: US17573568Application Date: 2022-01-11
-
Publication No.: US11943460B2Publication Date: 2024-03-26
- Inventor: Yadong Lu , Yang Yang , Yinhao Zhu , Amir Said , Reza Pourreza , Taco Sebastiaan Cohen
- Applicant: QUALCOMM Incorporated
- Applicant Address: US CA San Diego
- Assignee: QUALCOMM INCORPORATED
- Current Assignee: QUALCOMM INCORPORATED
- Current Assignee Address: US CA San Diego
- Agency: Seyfarth Shaw LLP
- Main IPC: H04N19/42
- IPC: H04N19/42 ; H04N19/124 ; H04N19/13 ; H04N19/136 ; H04N19/30 ; H04N19/36

Abstract:
A computer-implemented method for operating an artificial neural network (ANN) includes receiving an input by the ANN. The ANN generates a latent representation of the input. The latent representation is communicated according to a bit rate based on a learned latent scaling parameter. The latent scaling parameter is learned based on a channel index and a tradeoff parameter value that corresponds to a value that balances the bit rate and a distortion.
Public/Granted literature
- US20220224926A1 VARIABLE BIT RATE COMPRESSION USING NEURAL NETWORK MODELS Public/Granted day:2022-07-14
Information query