IEPT: Instance-Level and Episode-Level Pretext Tasks for Few-Shot Learning

Manli Zhang, Jianhong Zhang, Zhiwu Lu, Tao Xiang, Mingyu Ding, Songfang Huang

Keywords: few-shot learning, self-supervised learning, episode-level pretext task

Abstract: The need of collecting large quantities of labeled training data for each new task has limited the usefulness of deep neural networks. Given data from a set of source tasks, this limitation can be overcome using two transfer learning approaches: few-shot learning (FSL) and self-supervised learning (SSL). The former aims to learn `how to learn' by designing learning episodes using source tasks to simulate the challenge of solving the target new task with few labeled samples. In contrast, the latter exploits an annotation-free pretext task across all source tasks in order to learn generalizable feature representations. In this work, we propose a novel Instance-level and Episode-level Pretext Task (IEPT) framework that seamlessly integrates SSL into FSL. Specifically, given an FSL episode, we first apply geometric transformations to each instance to generate extended episodes. At the instance-level, transformation recognition is performed as per standard SSL. Importantly, at the episode-level, two SSL-FSL hybrid learning objectives are devised: (1) The consistency across the predictions of an FSL classifier from different extended episodes is maximized as an episode-level pretext task. (2) The features extracted from each instance across different episodes are integrated to construct a single FSL classifier for meta-learning. Extensive experiments show that our proposed model (i.e., FSL with IEPT) achieves the new state-of-the-art.

One-sentence Summary: This paper proposes a novel Instance-level and Episode-level Pretext Task (IEPT) framework that seamlessly integrates SSL into FSL.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Code: [ rucmlcv/IEPT_FSL](https://github.com/rucmlcv/IEPT_FSL)

Data: [mini-Imagenet](https://paperswithcode.com/dataset/mini-imagenet), [tieredImageNet](https://paperswithcode.com/dataset/tieredimagenet)