Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Coupled multi-task fully convolutional networks using multi-scale contextual information and hierarchical hyper-features for semantic image segmentation

Coupled multi-task fully convolutional networks using multi-scale contextual information and hierarchical hyper-features for semantic image segmentation

US Patent 10929977 · Granted Feb 23, 2021

Estimated economic value: $31,062,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Poly-scale kernel-wise convolution for high-performance visual recognition appli2025
Methods and apparatus for modifying a machine learning model2025
Compute optimizations for neural networks2025
Multicore processor with each core having independent floating point datapath an2025
Method and system of image hashing object detection for image processing2025
Method and system of image hashing object detection for image processing2025
Showerhead with massage function2025
Compute optimizations for low precision machine learning operations2025
Dynamic precision for neural network compute operations2025
Genome editing in plants2025
Input image size switchable network for adaptive runtime efficient image classif2025
Apparatus and methods for three-dimensional pose estimation2025