---
title: "Conditional Self-Supervised Learning for Few-Shot Classification"
authors:
  - "Yuexuan An"
  - "Hui Xue"
  - "Xingyu Zhao"
  - "Lu Zhang"
doi: "10.24963/ijcai.2021/295"
url: "https://ijcai.org/proceedings/2021/295"
pdf: "https://ijcai.org/proceedings/2021/0295.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "2140-2146"
track: "Main Track"
keywords:
  - "Machine Learning: Unsupervised Learning"
  - "Machine Learning: Classification"
  - "Machine Learning: Transfer, Adaptation, Multi-task Learning"
---

# Conditional Self-Supervised Learning for Few-Shot Classification

Yuexuan An, Hui Xue, Xingyu Zhao, Lu Zhang

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 2140-2146. DOI: [10.24963/ijcai.2021/295](https://doi.org/10.24963/ijcai.2021/295)

## 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.