FSU Computer Science Assistant Professor, Dr. Shayok Chakraborty, has received the Amazon Research Award for his project “Deep Active Learning with Relative Label Feedback”. Deep learning algorithms have created a paradigm shift in multimedia computing applications and have depicted tremendous performance improvements in a variety of computer vision tasks. However, training a robust deep neural network necessitates a large amount of hand-labeled training data, which is time-consuming and labor-intensive to acquire. The goal of this project is to develop efficient active learning algorithms to automatically identify the salient and exemplar instances from large amounts of unlabeled data; this will tremendously reduce the human annotation effort in inducing a deep model, as only a few samples, which are identified by the algorithm, need to be labeled manually.
The award includes funding in the amount of $73,000 for one year.