Cadence Design Systems, Inc.

Santa Clara University

Kwai Inc.

Omnivision Technologies, Inc.

Ming Kai Hsu

Ying Liu

Lingzhi Liu

Nam Ling

Yongxiong Ren

Yifei Pei

Sandip Parikh

Pengli Du

A class-specific neural network for video compressed sensing and methods for training and testing the class-specific neural network are provided. The class-specific neural network includes a Gaussian-mixture model (GMM) and a plurality of encoders, where the GMM classifies video frame blocks with a plurality of clusters and assigns the video frame blocks to the plurality of clusters. Further, the plurality of encoders receive the video frame blocks and generate a plurality of compressed-sensed frame block vectors, where the plurality of encoders correspond to the plurality of clusters.

Class-specific neural network for video compressed sensing

A method and an apparatus for video processing are provided. The method includes that a decoding terminal receives a plurality of coded video frames coded using one or more generative adversarial networks (GANs), receives network parameters related to the one or more GANs, and decodes the plurality of coded video frames using GANs based on the network parameters. Further, the one or more GANs respectively implement one or more video coding functions including reference-frame coding, motion-compensated frame prediction, and residue-frame coding.

Generative adversarial network for video compression

Quantized softmax layers in neural networks are described. Some embodiments involve receiving, at an input to a softmax layer of a neural network from an intermediate layer of the neural network, a non-normalized output comprising a plurality of intermediate network decision values. Then for each intermediate network decision value of the plurality of intermediate network decision values, the embodiment involves: calculating a difference between the intermediate network decision value and a maximum network decision value; requesting, from a lookup table, a corresponding lookup table value using the difference between the intermediate network decision value and the maximum network decision value; and selecting the corresponding lookup table value as a corresponding decision value. A normalized output is then generated comprising the corresponding lookup table value for said each intermediate network decision value of the plurality of intermediate network decision values.

Quantized softmax layer for neural networks

Various embodiments provide for quantizing a trained neural network with removal of normalization with respect to at least one layer of the quantized neural network, such as a quantized multiple fan-in layer (e.g., element-wise add or sum layer).

Quantizing trained neural networks with removal of normalization

Aspects of the present disclosure address systems and methods for fixed-point quantization using a dynamic quantization level adjustment scheme. Consistent with some embodiments, a method comprises accessing a neural network comprising floating-point representations of filter weights corresponding to one or more convolution layers. The method further includes determining a peak value of interest from the filter weights and determining a quantization level for the filter weights based on a number of bits in a quantization scheme. The method further includes dynamically adjusting the quantization level based on one or more constraints. The method further includes determining a quantization scale of the filter weights based on the peak value of interest and the adjusted quantization level. The method further includes quantizing the floating-point representations of the filter weights using the quantization scale to generate fixed-point representations of the filter weights.

Constraint-based dynamic quantization adjustment for fixed-point processing

A system for evaluating a classifier of an image signal processor (ISP) includes (i) a microprocessor and (ii) memory storing training images, the microprocessor being capable of sending each training image to the ISP. The system includes machine-readable instructions stored within the memory and executed by the microprocessor capable of: (i) selecting a subset of images based upon a divider position, (ii) controlling the ISP to classify each image as belonging or not belonging to an object class, (iii) determining a positive-match count, (iv) determining an error count based upon the positive-match count and total number of training images belonging to the object class, (v) repeating, for other divider positions, steps of selecting, controlling, and determining to identify an optimal divider position and a minimum-error count; and (vi) determining the classifier's optimality by comparing the optimal divider position to a predetermined optimal divider position and a predetermined minimum-error count.

Growing community of inventors

Fremont, CA, United States of America

Ming Kai Hsu