Temporal feature scaling for neural network processing
AssigneeSnap Inc.
InventorsSteven Roos, Zeqi Zhu, Orlando Miguel Pires dos Reis Moreira
Life of this patent
Estimating the term…
Loading patent…
AssigneeSnap Inc.
InventorsSteven Roos, Zeqi Zhu, Orlando Miguel Pires dos Reis Moreira
Estimating the term…
Systems, devices, and methods described herein relate to feature scaling for neural network processing. In some examples, temporal feature scaling is employed for efficient neural network processing. To process the neural network, a processing system accesses feature maps of a current input frame in a temporal sequence of input frames and scales the feature maps of the current input frame using excitation values generated from a previous input frame in the temporal sequence. The processing system generates new excitation values from the current input frame to perform scaling for a subsequent input frame in the temporal sequence.
A method for processing a temporal sequence of input frames through a neural network, the method performed by at least one processor and comprising:
A system comprising:
One or more non-transitory machine-readable storage media including instructions that, when executed by one or more processors, cause the one or more processors to perform operations for processing a temporal sequence of input frames through a neural network, the operations comprising:
Dependencies are inferred from the claim text.