Invention Application
- Patent Title: FEEDBACKWARD DECODER FOR PARAMETER EFFICIENT SEMANTIC IMAGE SEGMENTATION
-
Application No.: US17623714Application Date: 2020-06-30
-
Publication No.: US20220262002A1Publication Date: 2022-08-18
- Inventor: Beinan WANG , John GLOSSNER , Sabin Daniel IANCU
- Applicant: Optimum Semiconductor Technologies Inc.
- Applicant Address: US NY Tarrytown
- Assignee: Optimum Semiconductor Technologies Inc.
- Current Assignee: Optimum Semiconductor Technologies Inc.
- Current Assignee Address: US NY Tarrytown
- International Application: PCT/US2020/040236 WO 20200630
- Main IPC: G06T7/10
- IPC: G06T7/10 ; G06T3/40

Abstract:
A system and method relating to constructing an encoder and decoder neural network for providing semantic image segmentation includes generating an encoder comprising encoding convolution layers, each of the encoding convolution layers specifying an encoding filter operation using a respective first filter kernel, generating a decoder corresponding to the encoder, the decoder comprising decoding convolution layers, each of the decoding convolution layers being associated with a corresponding encoding convolution layer, and each of the decoding convolution layers specifying a decoding filter operation using a respective second filter kernel derived from the first filter kernel of the corresponding encoder convolution layer, and providing an input image to the encoder and the decoder for semantic image segmentation.
Information query