Implicit neural representations are a promising new avenue of representing general signals by learning a continuous function that, parameterized as a neural network, maps the domain of a signal to its codomain; the mapping from spatial coordinates of an image to its pixel values, for example.
As a result, we find across various workloads of data set, network model, and optimization algorithm that there exists a general scaling trend between batch size and number of training steps to convergence for the effect of data parallelism, and further, difficulty of training under sparsity.
Alternatively, a recent approach shows that pruning can be done at initialization prior to training, based on a saliency criterion called connection sensitivity.
To achieve this, we introduce a saliency criterion based on connection sensitivity that identifies structurally important connections in the network for the given task.
We propose an end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification.
DESIRE effectively predicts future locations of objects in multiple scenes by 1) accounting for the multi-modal nature of the future prediction (i. e., given the same context, future may vary), 2) foreseeing the potential future outcomes and make a strategic prediction based on that, and 3) reasoning not only from the past motion history, but also from the scene context as well as the interactions among the agents.
Ranked #1 on Trajectory Prediction on PAID
We introduce the concept of a Visual Compiler that generates a scene specific pedestrian detector and pose estimator without any pedestrian observations.
We develop predictive models of pedestrian dynamics by encoding the coupled nature of multi-pedestrian interaction using game theory, and deep learning-based visual analysis to estimate person-specific behavior parameters.