Abstract: The technology employs a patch-based multi-scale Transformer (300) that is usable with various imaging applications. This avoids constraints on image fixed input size and predicts the quality effectively on a native resolution image. A native resolution image (304) is transformed into a multi-scale representation (302), enabling the Transformer's self-attention mechanism to capture information on both fine-grained detailed patches and coarse-grained global patches. Spatial embedding (316) is employed to map patch positions to a fixed grid, in which patch locations at each scale are hashed to the same grid. A separate scale embedding (318) is employed to distinguish patches coming from different scales in the multiscale representation. Self-attention (508) is performed to create a final image representation. In some instances, prior to performing self-attention, the system may prepend a learnable classification token (322) to the set of input tokens.

Abstract: The technology employs a patch-based multi-scale Transformer (300) that is usable with various imaging applications. This avoids constraints on image fixed input size and predicts the quality effectively on a native resolution image. A native resolution image (304) is transformed into a multi-scale representation (302), enabling the Transformer's self-attention mechanism to capture information on both fine-grained detailed patches and coarse-grained global patches. Spatial embedding (316) is employed to map patch positions to a fixed grid, in which patch locations at each scale are hashed to the same grid. A separate scale embedding (318) is employed to distinguish patches coming from different scales in the multiscale representation. Self-attention (508) is performed to create a final image representation. In some instances, prior to performing self-attention, the system may prepend a learnable classification token (322) to the set of input tokens.

Abstract: A method for generating, for a video stream of a first spatial resolution and a first temporal resolution, a first reduced quality steam of a second spatial resolution and a second reduced-quality stream of a second temporal resolution. A first subset of STPs is sampled from the first reduced-quality stream and a second subset of STPs is sampled from the second reduced-quality stream. Using a machine learning model (MLM) the STPs are processed to identify a quality score for each quality-representative STPs that are representative of a quality of the video stream. One or more quality-improving actions for the video stream are identified using the quality scores of the quality-representative STPs.

Abstract: A method for a cross-platform distillation framework includes obtaining a plurality of training samples. The method includes generating, using a student neural network model executing on a first processing unit, a first output based on a first training sample. The method also includes generating, using a teacher neural network model executing on a second processing unit, a second output based on the first training sample. The method includes determining, based on the first output and the second output, a first loss. The method further includes adjusting, based on the first loss, one or more parameters of the student neural network model. The method includes repeating the above steps for each training sample of the plurality of training samples.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing a network input using a neural network to generate a network output. The neural network includes a normalization block that is between a first neural network layer and a second neural network layer in the neural network. Processing the network input using the neural network comprises: receiving a first layer output from the first neural network layer; processing data derived from the first layer output using standardization neural network layers of the normalization block to generate one or more adaptive standardization values; standardizing the first layer output using the adaptive standardization values to generate a standardized first layer output; generating a normalization block output from the standardized first layer output; and providing the normalization block output as an input to the second neural network layer.

Abstract: The technology employs a patch-based multi-scale Transformer (300) that is usable with various imaging applications. This avoids constraints on image fixed input size and predicts the quality effectively on a native resolution image. A native resolution image (304) is transformed into a multi-scale representation (302), enabling the Transformer's self-attention mechanism to capture information on both fine-grained detailed patches and coarse-grained global patches. Spatial embedding (316) is employed to map patch positions to a fixed grid, in which patch locations at each scale are hashed to the same grid. A separate scale embedding (318) is employed to distinguish patches coming from different scales in the multiscale representation. Self-attention (508) is performed to create a final image representation. In some instances, prior to performing self-attention, the system may prepend a learnable classification token (322) to the set of input tokens.

Abstract: The technology employs a patch-based multi-scale Transformer (300) that is usable with various imaging applications. This avoids constraints on image fixed input size and predicts the quality effectively on a native resolution image. A native resolution image (304) is transformed into a multi-scale representation (302), enabling the Transformer's self-attention mechanism to capture information on both fine-grained detailed patches and coarse-grained global patches. Spatial embedding (316) is employed to map patch positions to a fixed grid, in which patch locations at each scale are hashed to the same grid. A separate scale embedding (318) is employed to distinguish patches coming from different scales in the multiscale representation. Self-attention (508) is performed to create a final image representation. In some instances, prior to performing self-attention, the system may prepend a learnable classification token (322) to the set of input tokens.

Abstract: A method includes obtaining a first plurality of feature vectors associated with a first image and a second plurality of feature vectors associated with a second image. The method also includes generating a plurality of transformed feature vectors by transforming each respective feature vector of the first plurality of feature vectors by a kernel matrix trained to define an elliptical inner product space. The method additionally includes generating a cost volume by determining, for each respective transformed feature vector of the plurality of transformed feature vectors, a plurality of inner products, wherein each respective inner product of the plurality of inner products is between the respective transformed feature vector and a corresponding candidate feature vector of a corresponding subset of the second plurality of feature vectors. The method further includes determining, based on the cost volume, a pixel correspondence between the first image and the second image.

Abstract: Systems and methods of the present disclosure are directed to a method for generating a machine-learned multitask model configured to perform tasks. The method can include obtaining a machine-learned multitask search model comprising candidate nodes. The method can include obtaining tasks and machine-learned task controller models associated with the tasks. As an example, for a task, the method can include using the task controller model to route a subset of the candidate nodes in a machine-learned task submodel for the corresponding task. The method can include inputting task input data to the task submodel to obtain a task output. The method can include generating, using the task output, a feedback value based on an objective function. The method can include adjusting parameters of the task controller model based on the feedback value.

Abstract: The technology employs a patch-based multi-scale Transformer (300) that is usable with various imaging applications. This avoids constraints on image fixed input size and predicts the quality effectively on a native resolution image. A native resolution image (304) is transformed into a multi-scale representation (302), enabling the Transformer's self-attention mechanism to capture information on both fine-grained detailed patches and coarse-grained global patches. Spatial embedding (316) is employed to map patch positions to a fixed grid, in which patch locations at each scale are hashed to the same grid. A separate scale embedding (318) is employed to distinguish patches coming from different scales in the multiscale representation. Self-attention (508) is performed to create a final image representation. In some instances, prior to performing self-attention, the system may prepend a learnable classification token (322) to the set of input tokens.

Abstract: The present disclosure is directed to object and/or character recognition for use in applications such as computer vision. Advantages of the present disclosure include lightweight functionality that can be used on devices such as smart phones. Aspects of the present disclosure include a sequential architecture where a lightweight machine-learned model can receive an image, detect whether an object is present in one or more regions of the image, and generate an output based on the detection. This output can be applied as a filter to remove image data that can be neglected for more memory intensive machine-learned models applied downstream.

Abstract: A method includes obtaining a first plurality of feature vectors associated with a first image and a second plurality of feature vectors associated with a second image. The method also includes generating a plurality of transformed feature vectors by transforming each respective feature vector of the first plurality of feature vectors by a kernel matrix trained to define an elliptical inner product space. The method additionally includes generating a cost volume by determining, for each respective transformed feature vector of the plurality of transformed feature vectors, a plurality of inner products, wherein each respective inner product of the plurality of inner products is between the respective transformed feature vector and a corresponding candidate feature vector of a corresponding subset of the second plurality of feature vectors. The method further includes determining, based on the cost volume, a pixel correspondence between the first image and the second image.

Abstract: An application software installation method and an application software installation apparatus are used to solve problems of operation complexity and high implementation difficulty in an existing installation process of application software. The method includes: mounting mirror data of a virtual machine, and mapping the mirror data as one virtual disk in a local file system; updating a registry file in a virtual disk according to registry change record data in an application software package; and updating a file structure in the virtual disk according to the file change record data and the file in the application software package, thereby implementing installation of the application software in the virtual machine. In the process of installing the application software, a user of the virtual machine does not need to perform complex operations, thereby reducing software installation difficulty.