{"type":"ScholarlyArticle","title":"Conditional Self-Supervised Learning for Few-Shot Classification","authors":[{"name":"Yuexuan An","slug":"yuexuan-an","given":"Yuexuan","family":"An","affiliation":""},{"name":"Hui Xue","slug":"hui-xue","given":"Hui","family":"Xue","affiliation":""},{"name":"Xingyu Zhao","slug":"xingyu-zhao","given":"Xingyu","family":"Zhao","affiliation":""},{"name":"Lu Zhang","slug":"lu-zhang","given":"Lu","family":"Zhang","affiliation":""}],"abstract":"How to learn a transferable feature representation from limited examples is a key challenge for few-shot classification. Self-supervision as an auxiliary task to the main supervised few-shot task is considered to be a conceivable way to solve the problem since self-supervision can provide additional structural information easily ignored by the main task. However, learning a good representation by traditional self-supervised methods is usually dependent on large training samples. In few-shot scenarios, due to the lack of sufficient samples, these self-supervised methods might learn a biased representation, which more likely leads to the wrong guidance for the main tasks and finally causes the performance degradation. In this paper, we propose conditional self-supervised learning (CSS) to use auxiliary information to guide the representation learning of self-supervised tasks. Specifically, CSS leverages supervised information as prior knowledge to shape and improve the learning feature manifold of self-supervision without auxiliary unlabeled data, so as to reduce representation bias and mine more effective semantic information. Moreover, CSS exploits more meaningful information through supervised and the improved self-supervised learning respectively and integrates the information into a unified distribution, which can further enrich and broaden the original representation. Extensive experiments demonstrate that our proposed method without any fine-tuning can achieve a significant accuracy improvement on the few-shot classification scenarios compared to the state-of-the-art few-shot learning methods.","doi":"10.24963/ijcai.2021/295","url":"https://ijcai.org/proceedings/2021/295","pdf":"https://ijcai.org/proceedings/2021/0295.pdf","markdown":"https://ijcai.org/proceedings/2021/295.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/295","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Machine Learning","track":"Main Track","number":295,"pages":{"first":2140,"last":2146},"keywords":["Machine Learning: Unsupervised Learning","Machine Learning: Classification","Machine Learning: Transfer, Adaptation, Multi-task Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}