Abstract: Systems and methods are disclosed for capturing multiple sequences of views of a three-dimensional object using a plurality of virtual cameras. The systems and methods generate aligned sequences from the multiple sequences based on an arrangement of the plurality of virtual cameras in relation to the three-dimensional object. Using a convolutional network, the systems and methods classify the three-dimensional object based on the aligned sequences and identify the three-dimensional object using the classification.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for balanced-weight sparse convolution processing. An exemplary method comprises: obtaining an input tensor and a plurality of filters at a layer within a neural network; segmenting the input tensor into a plurality of sub-tensors; dividing a channel dimension of each of the plurality of filters into a plurality of channel groups; pruning each of the plurality of filters so that each of the plurality of channel groups of each filter comprises a same number of non-zero weights; segmenting each of the plurality of filters into a plurality of the sub-filters according to the plurality of channel groups; and assigning the plurality of sub-tensors and the plurality of sub-filters to a plurality of processors for parallel convolution processing.

Abstract: Systems and methods are disclosed for capturing multiple sequences of views of a three-dimensional object using a plurality of virtual cameras. The systems and methods generate aligned sequences from the multiple sequences based on an arrangement of the plurality of virtual cameras in relation to the three-dimensional object. Using a convolutional network, the systems and methods classify the three-dimensional object based on the aligned sequences and identify the three-dimensional object using the classification.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for improving efficiency of neural network computations using adaptive tensor compute kernels. First, the adaptive tensor compute kernels may adjust shapes according to the different shapes of input/weight tensors for distributing the weights and input values to a processing elements (PE) array for parallel processing. Depending on the shape of the tensor compute kernels, additional inter-cluster or intra-cluster adders may be needed to perform convolution computations. Second, the adaptive tensor compute kernels may support two different tensor operation modes, i.e., 1×1 tensor operation mode and 3×3 tensor operation mode, to cover all types of convolution computations. Third, the underlying PE array may configure each PE-internal buffer (e.g., a register file) differently to support different compression ratios and sparsity granularities of sparse neural networks.

Abstract: Aspects of the present disclosure involve a system comprising a storage medium storing a program and method for receiving a video comprising a plurality of video segments; selecting a target action sequence that includes a sequence of action phases; receiving features of each of the video segments; computing, based on the received features, for each of the plurality of video segments, a plurality of action phase confidence scores indicating a likelihood that a given video segment includes a given action phase of the sequence of action phases; identifying a set of consecutive video segments of the plurality of video segments that corresponds to the target action sequence, wherein video segments in the set of consecutive video segments are arranged according to the sequence of action phases; and generating a display of the video that includes the set of consecutive video segments and skips other video segments in the video.

Abstract: A neural network pruning system can sparsely prune neural network models using an optimizer based approach that is agnostic to the model architecture being pruned. The neural network pruning system can prune by operating on the parameter vector of the full model and the gradient vector of the loss function with respect to the model parameters. The neural network pruning system can iteratively update parameters based on the gradients, while zeroing out as many parameters as possible based a preconfigured penalty.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for parallelizing convolution processing. An exemplary method comprises: segmenting an input tensor into a plurality of sub-tensors and a plurality of filters into a plurality of sub-filter groups; respectively assigning a plurality of combinations of the sub-tensors and the sub-filter groups to a plurality of processors; storing, by each of the plurality of processors, nonzero values of the sub-tensor and the sub-filter group in the assigned combination as index-value pairs; parallelly performing for a plurality of iterations, by the plurality of processors, multiply-and-accumulate (MAC) operations based on the index-value pairs to obtain a plurality of outputs, where the index-value pairs of the sub-filter groups are rotated among the plurality of processors across the plurality of iterations; and aggregating the plurality of outputs as an output tensor.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for few-shot learning-based generator training are disclosed. An exemplary method may start with obtaining a teacher model and a plurality of training samples, as well as a generator for generating more training samples. After generating a plurality of additional training samples using the method may continue with feeding the plurality of generated additional training samples into the teacher model to obtain a plurality of first statistics; and feeding the plurality of training samples into the teacher model to obtain a plurality second statistics. Then the method further includes training the generator to minimize a distance between the plurality of first statistics and the plurality of second statistics.

Abstract: A neural network pruning system can sparsely prune neural network models using an optimizer based approach that is agnostic to the model architecture being pruned. The neural network pruning system can prune by operating on the parameter vector of the full model and the gradient vector of the loss function with respect to the model parameters. The neural network pruning system can iteratively update parameters based on the gradients, while zeroing out as many parameters as possible based a preconfigured penalty.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for few-shot learning-based generator training based on raw data collected from a specific domain or class. In cases where the raw data is collected from multiple domains but is not easily divisible into classes, the invention describes training multiple generators based on a pivot-sample-based training process. Pivot samples are randomly selected from the raw data for clustering, and each cluster of raw data may be used to train a generator using the few-shot learning-based training process.

Abstract: Systems and methods are disclosed for capturing multiple sequences of views of a three-dimensional object using a plurality of virtual cameras. The systems and methods generate aligned sequences from the multiple sequences based on an arrangement of the plurality of virtual cameras in relation to the three-dimensional object. Using a convolutional network, the systems and methods classify the three-dimensional object based on the aligned sequences and identify the three-dimensional object using the classification.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for optimizing neural network training, are described. The method may include: during a forward propagation at a current layer of a neural network, generating, based on a sparse input tensor and a sparse weight tensor of the current layer, a dense output tensor, and sparsifying the dense output tensor to obtain a sparse output tensor; during a backward propagation at the current layer of the neural network: determining a first sparse derivative tensor based on the sparse output tensor, obtaining a dense derivative tensor based on the first sparse derivative tensor and the sparse weight tensor of the current layer, and sparsifying the dense derivative tensor to obtain a second sparse derivative tensor; and training weight tensors of the neural network based on the first sparse derivative tensor and the second sparse derivative tensor.

Abstract: Systems and methods are disclosed for capturing multiple sequences of views of a three-dimensional object using a plurality of virtual cameras. The systems and methods generate aligned sequences from the multiple sequences based on an arrangement of the plurality of virtual cameras in relation to the three-dimensional object. Using a convolutional network, the systems and methods classify the three-dimensional object based on the aligned sequences and identify the three-dimensional object using the classification.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for domain-specific pruning of neural networks are described. An exemplary method includes obtaining a first neural network trained based on a first training dataset; obtaining one or more second training datasets respectively from one or more domains; and training, based on the first neural network and the one or more second training datasets, a second neural network comprising the first neural network and one or more branches extended from the first neural network, wherein the second neural network is applicable for inferencing in the one or more domains, and the training comprises: training the one or more branches based respectively on the one or more second training datasets and an output of the first neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for domain-specific pruning of neural networks are described. An exemplary method includes obtaining a first neural network trained based on a first training dataset; obtaining one or more second training datasets respectively from one or more domains; and training, based on the first neural network and the one or more second training datasets, a second neural network comprising the first neural network and one or more branches extended from the first neural network, wherein the second neural network is applicable for inferencing in the one or more domains, and the training comprises: training the one or more branches based respectively on the one or more second training datasets and an output of the first neural network.

Abstract: Embodiments disclosed herein allowed neural networks to be pruned. The inputs and outputs generated by a reference neural network are used to prune the reference neural network. The pruned neural network may have a subset of the weights that are in the reference neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for convolution with workload-balanced activation sparsity are described. An exemplary method comprises: assigning an input tensor and a weight tensor at a convolution layer into a plurality of processors to perform Multiply-Accumulate (MAC) operations in parallel based on the input tensor and the weight tensor; obtaining a plurality of output values based on results of the MAC operations; constructing one or more banks of output values based on the plurality of output values; for each of the banks, performing a top-K sorting on the one or more output values in the bank to obtain K output values; pruning each of the banks by setting the one or more output values other than the obtained K output values in the each bank as zeros; and constructing an output tensor of the convolution layer based on the pruned banks.

Abstract: Embodiments disclose bank-balanced-sparse activation neural network models and methods to generate the bank-balanced-sparse activation neural network models. According to one embodiment, a neural network sparsification engine determines a first deep neural network (DNN) model having two or more hidden layers. The engine determines a bank size, a bank layout, and a target sparsity. The engine segments the activation feature maps into a plurality of banks based on the bank size and the bank layout. The engine generates a second DNN model by increasing a sparsity for each bank of activation feature map based on the target sparsity, wherein the second DNN model is used for inferencing.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for balanced-weight sparse convolution processing. An exemplary method comprises: obtaining an input tensor and a plurality of filters at a layer within a neural network; segmenting the input tensor into a plurality of sub-tensors; dividing a channel dimension of each of the plurality of filters into a plurality of channel groups; pruning each of the plurality of filters so that each of the plurality of channel groups of each filter comprises a same number of non-zero weights; segmenting each of the plurality of filters into a plurality of the sub-filters according to the plurality of channel groups; and assigning the plurality of sub-tensors and the plurality of sub-filters to a plurality of processors for parallel convolution processing.

Abstract: Aspects of the present disclosure involve a system comprising a storage medium storing a program and method for receiving a video comprising a plurality of video segments; selecting a target action sequence that includes a sequence of action phases; receiving features of each of the video segments; computing, based on the received features, for each of the plurality of video segments, a plurality of action phase confidence scores indicating a likelihood that a given video segment includes a given action phase of the sequence of action phases; identifying a set of consecutive video segments of the plurality of video segments that corresponds to the target action sequence, wherein video segments in the set of consecutive video segments are arranged according to the sequence of action phases; and generating a display of the video that includes the set of consecutive video segments and skips other video segments in the video.