Invention Application
- Patent Title: INSTANCE SEGMENTATION WITH DEPTH AND BOUNDARY LOSSES
-
Application No.: US18326437Application Date: 2023-05-31
-
Publication No.: US20240404003A1Publication Date: 2024-12-05
- Inventor: Debasmit DAS , Hyojin PARK , Shubhankar Mangesh BORSE , Yu FU , Oleksandr BAILO , Mohsen GHAFOORIAN , Fatih Murat PORIKLI
- Applicant: QUALCOMM Incorporated
- Applicant Address: US CA San Diego
- Assignee: QUALCOMM Incorporated
- Current Assignee: QUALCOMM Incorporated
- Current Assignee Address: US CA San Diego
- Main IPC: G06T3/40
- IPC: G06T3/40

Abstract:
Certain aspects of the present disclosure provide techniques for training and using an instance segmentation neural network to detect instances of a target object in an image. An example method generally includes generating, through an instance segmentation neural network, a first mask output from a first mask generation branch of the network. The method further includes generating, through the instance segmentation neural network, a second mask output from a second, parallel, mask generation branch of the network. The second mask output is typically of a lower resolution than the first mask output. The method further includes combining the first mask output and second mask output to generate a combined mask output. Based on the combined mask output, an output of the instance segmentation neural network is generated. One or more actions are taken based on the generated output.
Information query