In this paper, we propose a novel self-supervised learning framework that combines contrastive learning with neural processes.
To overcome these limitations, we reformulate AutoAugment as a generalized automated dataset optimization (AutoDO) task that minimizes the distribution shift between test data and distorted train dataset.
We introduce DoorGym, an open-source door opening simulation framework designed to utilize domain randomization to train a stable policy.
In this paper, we introduce a method to compress intermediate feature maps of deep neural networks (DNNs) to decrease memory storage and bandwidth requirements during inference.
We also show that PI-Net is able to learn dynamics and cost models latent in the demonstrations.
In this paper we introduce ShiftCNN, a generalized low-precision architecture for inference of multiplierless convolutional neural networks (CNNs).
We address unsupervised optical flow estimation for ego-centric motion.
Multi-object tracking has recently become an important area of computer vision, especially for Advanced Driver Assistance Systems (ADAS).
Deep neural networks have recently achieved state of the art performance thanks to new training algorithms for rapid parameter estimation and new regularization methods to reduce overfitting.
We perform various experiments to assess the removability of adversarial examples by corrupting with additional noise and pre-processing with denoising autoencoders (DAEs).