首页|Patent Application Titled 'Adaptive Learning For Semantic Segmentation' Publishe d Online (USPTO 20240331368)
Patent Application Titled 'Adaptive Learning For Semantic Segmentation' Publishe d Online (USPTO 20240331368)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – According to news reporting originatin g from Washington, D.C., by NewsRx journalists, a patent application by the inve ntors Cremieux, Matthias (Paris, FR); Salman, Nader (Houston, TX, US), filed on October 27, 2022, was made available online on October 3, 2024. No assignee for this patent application has been made.Reporters obtained the following quote from the background information supplied by the inventors: “Machine learning automation of data inspection tasks (e.g., m anufacturing asset imaging, satellite imagery, seismic imaging, medical imaging, etc.) using various imaging modalities (RGB, Infrared, Multi- Spectral . . . ) a nd employing precise pixel level labeling typically includes a bottleneck at the labeling stage. In the inspection domain, large amounts of data may be generate d, but most of the data is not readily used for machine learning purposes. That is, the data is unlabeled, and labeling the data generally calls for human subje ct matter experts to label the high-resolution images at a per pixel level. Vari ous techniques have been used to increase the efficiency of this task (e.g., wat er shedding), but it remains a time-intensive activity that increases the costs for such automation projects.”
NETL
NSTL
