Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an output that characterizes a scene at a current time step. In one aspect, one of the systems include: a voxel neural network that generates a current early-stage feature representation of the current point cloud, a fusion subsystem that generates a current fused feature representation at the current time step; a backbone neural network that generates a current late-stage feature representation at the current time step, and an output neural network that generate an output that characterizes a scene at the current time step.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model on training data. In one aspect, one of the methods include: obtaining a training data set comprising a plurality of training inputs; obtaining data defining an original search space of a plurality of candidate data augmentation policies; generating, from the original search space, a compact search space that has one or more global hyperparameters; and training the machine learning model on the training data using one or more final data augmentation policies generated from the compact search space.

Abstract: Methods, systems, and apparatus for processing point clouds using neural networks to perform a machine learning task. In one aspect, a system comprises one or more computers configured to obtain a set of point clouds captured by one or more sensors. Each point cloud includes a respective plurality of three-dimensional points. The one or more computers assign the three-dimensional points to respective voxels in a voxel grid, where the grid of voxels includes non-empty voxels to which one or more points are assigned and empty voxels to which no points are assigned. For each non-empty voxel, the one or more computers generate initial features based on the points that are assigned to the non-empty voxel. The one or more computers generate multi-scale features of the voxel grid, and the one or more computers generate an output for a point cloud processing task using the multi-scale features of the voxel grid.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for performing training of a neural network that is configured to process a network input comprising a point cloud to generate a network output for a point cloud processing task. The system obtains a set of labeled training examples and a set of unlabeled point clouds, generates a respective pseudo-label for each unlabeled point cloud, generates a plurality of pseudo-elements based on the respective pseudo-label for the unlabeled point cloud, generates augmented training data by augmenting the labeled training examples using the pseudo-elements generated for the unlabeled point clouds, and performing training of the neural network on the augmented training data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a machine learning model to perform a machine learning task by processing input data to the model. For example, the input data can include image, video, or point cloud data, and the task can be a perception task such as classification or detection task. In one aspect, the method includes receiving training data including a plurality of training inputs; receiving a plurality of data augmentation policy parameters that define different transformation operations for transforming training inputs before the training inputs are used to train the machine learning model; maintaining a plurality of candidate machine learning models; for each of the plurality of candidate machine learning models: repeatedly determining an augmented batch of training data; training the candidate machine learning model using the augmented batch of the training data; and updating the maintained data.