Learning with Limited Supervision for Static and Dynamic Tasks. A Dissertation submitted in partial satisfaction of the requirements for the degree of. Doctor ...

A pictorial overview of active learning is given in Fig. 3.1. Given a large unlabeled dataset, active learning methods first choose a small random subset of ...

We develop frameworks to learn using weak labels for action detection in videos and domain adaptation of semantic segmentation models on images. In action ...

Title: Learning with Limited Supervision for Static and Dynamic Tasks. Abstract. Most successes of computer vision have been around using a huge corpus of ...

Self-supervised learning (SSL) is an AI-based method of training algorithmic models on raw, unlabeled data. Using various methods and learning techniques, ...

Reinforcement Learning (RL) is the science of decision making. It is about learning the optimal behavior in an environment to obtain maximum reward.

Unlike unsupervised and supervised machine learning, reinforcement learning does not rely on a static dataset, but operates in a dynamic environment and learns ...

Abstract. In this paper, we propose a novel learning scheme for self- supervised video representation learning. Motivated by how humans un-.

Self- supervised learning is proven to be a powerful tool for learning representations that are useful to down-stream tasks without requiring labeled data.