Self Supervised Salient Object Detection using Pseudo-labels
Date
2023-08
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
University of the Witwatersrand, Johannesburg
Abstract
Deep Convolutional Neural Networks have dominated salient object detection methods in recent history. A determining factor for salient object detection network performance is the quality and quantity of pixel-wise annotated labels. This annotation is performed manually, making it expensive (time-consuming, tedious), while limiting the training data to the available annotated datasets. Alternatively, unsupervised models are able to learn from unlabelled datasets or datasets in the wild. In this work, an existing algorithm [Li et al. 2020] is used to refine the generated pseudo labels before training. This research focuses on the changes made to the pseudo label refinement algorithm and its effect on performance for unsupervised saliency object detection tasks. We show that using this novel approach leads to statistically negligible performance improvements and discuss the reasons why this is the case.
Description
A research report submitted in partial fulfilment of the requirements for the degree of Masters of Science, to the Faculty of Science, School of Computer Science & Applied Mathematics, University of the Witwatersrand, Johannesburg, 2023.
Keywords
Self supervised, Salient object detection, Pseudo-labels computer vision, UCTD
Citation
Bachan, Kidhar. (2023). Self Supervised Salient Object Detection using Pseudo-labels. [Master's dissertation, University of the Witwatersrand, Johannesburg]. https://hdl.handle.net/10539/42353