Abstract: A vehicle computing system may implement techniques to determine attributes (or intent) of an object detected by a vehicle operating in the environment. The techniques may include determining a set of features with respect to a detected object by a first model and determining, by a second model and based on the set of features, one or more attributes of the object. The first model and the second model may be configured to process at least one image frame to determine the one or more attributes of the object. A model may receive sensor data as an input, and output features and/or an attribute for the detected object. Based on the attribute(s) of the object, a vehicle computing system may control operation of the vehicle.

Abstract: Provided are systems and methods for sequence-to-sequence modeling with neural quality metrics. More particularly, example aspects of the present disclosure relate to minimum bayes risk (MBR) decoding with neural metrics for machine translation. According to example aspects of the present disclosure, a set of candidate outputs can be sampled from a machine translation model given a source sequence. Given the set of candidate outputs, systems and methods according to example aspects of the present disclosure can select a hypothesis with high expected utility with respect to the distribution over a set of pseudo-references from the machine translation model.

Abstract: Techniques for training a computationally-expensive layer, such as a convolutional layer, of a machine-learning model toward a target filter. If the training drives parameters associated with the layer to match or be close enough to the target filter, the layer may be removed, replace, and/or reduced in size, depending on the type of target filter used.

Abstract: Techniques for training a machine learning model are described herein. For example, the techniques may include implementing a cross batch normalization layer that generates a cross batch normalization layer output based on a first layer output during training of the neural network. The training may be based on a local batch of training examples of a global batch including the local batch and at least one remote batch of training examples. The cross batch normalization layer output may include normalized components of the first layer output determined based on global normalization statistics for the global batch. Such techniques may be used to train a neural network over distributed machines by synchronizing batches between such machines.

Abstract: A vehicle computing system may implement techniques to determine attributes (or intent) of an object detected by a vehicle operating in the environment. The techniques may include determining a set of features with respect to a detected object by a first model and determining, by a second model and based on the set of features, one or more attributes of the object. The first model and the second model may be configured to process at least one image frame to determine the one or more attributes of the object. A model may receive sensor data as an input, and output features and/or an attribute for the detected object. Based on the attribute(s) of the object, a vehicle computing system may control operation of the vehicle.

Abstract: A vehicle computing system may implement techniques to determine attributes (or intent) of an object detected by a vehicle operating in the environment. The techniques may include determining a set of features with respect to a detected object by a first model and determining, by a second model and based on the set of features, one or more attributes of the object. The first model and the second model may be configured to process at least one image frame to determine the one or more attributes of the object. A model may receive sensor data as an input, and output features and/or an attribute for the detected object. Based on the attribute(s) of the object, a vehicle computing system may control operation of the vehicle.

Abstract: A machine-learning (ML) architecture may comprise a first ML model and/or an optical flow model that receive, as input, a first image and a second image. The first ML model may output a first feature map corresponding to the first image and a second feature map corresponding to the second image. The optical flow model may output an estimated optical flow. A deformation component may modify the second feature map, as a deformed feature map, based at least in part on the estimated optical flow. The deformed feature map and the first feature map may be concatenated together as a concatenated feature map, which may be provided to a second ML model. The second ML model may be trained to output an output ROI and/or a track in association with an object represented in the first image.

Abstract: Techniques for compacting an ML model by replacing a linear transformation layer and a convolutional layer with a modified convolution layer. Determining the modified convolutional layer may include determining a modified bias and/or a modified filter. In some examples, before merging the layers, an output of the linear transformation layer may be provided as input to the convolution layer (e.g., the linear transformation layer may precede the convolutional layer). The linear transformation lay may include, for example, a batch normalization layer, a pooling layer, and/or the like.

Abstract: Techniques for training a machine learning model are described herein. For example, the techniques may include implementing a cross batch normalization layer that generates a cross batch normalization layer output based on a first layer output during training of the neural network. The training may be based on a local batch of training examples of a global batch including the local batch and at least one remote batch of training examples. The cross batch normalization layer output may include normalized components of the first layer output determined based on global normalization statistics for the global batch. Such techniques may be used to train a neural network over distributed machines by synchronizing batches between such machines.

Abstract: A machine-learning (ML) architecture may comprise a first ML model and/or an optical flow model that receive, as input, a first image and a second image. The first ML model may output a first feature map corresponding to the first image and a second feature map corresponding to the second image. The optical flow model may output an estimated optical flow. A deformation component may modify the second feature map, as a deformed feature map, based at least in part on the estimated optical flow. The deformed feature map and the first feature may be concatenated together as a concatenated feature map, which may be provided to a second ML model. The second ML model may be trained to output an output ROI and/or a track in association with an object represented in the first image.

Abstract: A machine-learning (ML) architecture may comprise a first ML model and/or an optical flow model that receive, as input, a first image and a second image. The first ML model may output a first feature map corresponding to the first image and a second feature map corresponding to the second image. The optical flow model may output an estimated optical flow. A deformation component may modify the second feature map, as a deformed feature map, based at least in part on the estimated optical flow. The deformed feature map and the first feature map may be concatenated together as a concatenated feature map, which may be provided to a second ML model. The second ML model may be trained to output an output ROI and/or a track in association with an object represented in the first image.