Date of Award
Master of Science (MS)
Deep learning (Machine learning), Pattern recognition systems, Image processing
In this thesis we address the problem of consensus based multi-label classification. In the general multi-label classification problem, an input is assigned to multiple classes without any constraints. However, there are applications where the multi-label classification needs to be solved under the constraint of a consensus among the assigned labels. We address this problem here using a deep learning approach. We conduct experiments with the MNIST dataset and establish the possibility of using such approaches for traditional multi-class problems. Furthermore, we demonstrate the use of our consensus based classifier in a generative adversarial framework for training a generator for handwritten digits. Our approach results in a lower loss and better quality generated images.
Acharya, Digya, "A deep learning framework for consensus based multilabel classification and image generation" (2022). Theses. 394.