An Approach to Self-Supervised Object Localisation through Deep Learning Based Classification

Deep learning has become ubiquitous in science and industry for classifying images or identifying patterns in data. The most widely used approach to training convolutional neural networks is supervised learning, which requires a large set of annotated data. To elude the high cost of collecting and annotating datasets, self-supervised learning methods represent a promising way to learn the common functions of images and videos from large-scale unlabeled data without using human-annotated labels. This thesis provides the results of using self-supervised learning and explainable AI to localise objects in images from electron microscopes. The work used a synthetic geometric dataset and a synthetic pollen dataset. The classifica-tion was used as a pretext task. Different methods of explainable AI were applied: Grad-CAM and backpropagation-based approaches showed the lack of prospects; at the same time, the Extremal Perturbation function has shown efficiency. As a result of the downstream localisation task, the objects of interest were detected with competitive accuracy for one-class images. The advantages and limitations of the approach have been analysed. Directions for further work are proposed.