Recent advancements in self-supervised paradigms for visual feature representation

Show simple item record

dc.contributor.author Anand, Mrinal
dc.contributor.author Garg, Aditya
dc.date.accessioned 2021-11-24T13:31:13Z
dc.date.available 2021-11-24T13:31:13Z
dc.date.issued 2021-11
dc.identifier.citation Anand, Mrinal and Garg, Aditya, "Recent advancements in self-supervised paradigms for visual feature representation", arXiv, Cornell University Library, DOI: arXiv:2111.02042, Nov. 2021 en_US
dc.identifier.uri http://arxiv.org/abs/2111.02042
dc.identifier.uri https://repository.iitgn.ac.in/handle/123456789/7288
dc.description.abstract We witnessed a massive growth in the supervised learning paradigm in the past decade. Supervised learning requires a large amount of labeled data to reach state-of-the-art performance. However, labeling the samples requires a lot of human annotation. To avoid the cost of labeling data, self-supervised methods were proposed to make use of largely available unlabeled data. This study conducts a comprehensive and insightful survey and analysis of recent developments in the self-supervised paradigm for feature representation. In this paper, we investigate the factors affecting the usefulness of self-supervision under different settings. We present some of the key insights concerning two different approaches in self-supervision, generative and contrastive methods. We also investigate the limitations of supervised adversarial training and how self-supervision can help overcome those limitations. We then move on to discuss the limitations and challenges in effectively using self-supervision for visual tasks. Finally, we highlight some open problems and point out future research directions
dc.description.statementofresponsibility by Mrinal Anand and Aditya Garg
dc.language.iso en_US en_US
dc.publisher Cornell University Library en_US
dc.subject Computer Vision and Pattern Recognition en_US
dc.subject Machine Learning en_US
dc.subject Artificial Intelligence en_US
dc.title Recent advancements in self-supervised paradigms for visual feature representation en_US
dc.type Pre-Print en_US
dc.relation.journal arXiv


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Digital Repository


Browse

My Account