University of Oulu

Cui, Y., Liao, Q., Hu, D., An, W., & Liu, L. (2022). Coarse-to-fine pseudo supervision guided meta-task optimization for few-shot object classification. Pattern Recognition, 122, 108296.

Coarse-to-fine pseudo supervision guided meta-task optimization for few-shot object classification

Saved in:
Author: Cui, Yawen1; Liao, Qing2; Hu, Dewen3;
Organizations: 1Center for Machine Vision and Signal Analysis, University of Oulu, Finland
2Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China
3College of Intelligent Science, National University of Defense Technology, Changsha, China
4College of Electronic Science and Technology, National University of Defense Technology, Changsha, China
5College of System Engineering, National University of Defense Technology, Changsha, China
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 1.5 MB)
Persistent link:
Language: English
Published: Elsevier, 2022
Publish Date: 2023-10-17


Few-Shot Learning (FSL) is a challenging and practical learning pattern, aiming to solve a target task which has only a few labeled examples. Currently, the field of FSL has made great progress, but largely in the supervised setting, where a large auxiliary labeled dataset is required for offline training. However, the unsupervised FSL (UFSL) problem where the auxiliary dataset is fully unlabeled has been seldom investigated despite of its significant value. This paper focuses on the more general and challenging UFSL problem and presents a novel method named Coarse-to-Fine Pseudo Supervision-guided Meta-Learning (C2FPS-ML) for unsupervised few-shot object classification. It first obtains prior knowledge from an unlabeled auxiliary dataset during unsupervised meta-training, and then use the prior knowledge to assist the downstream few-shot classification task. Coarse-to-Fine Pseudo Supervisions in C2FPS-ML aim to optimize meta-task sampling process in unsupervised meta-training stage which is one of the dominant factors for improving the performance of meta-learning based FSL algorithms. Human can learn new concepts progressively or hierarchically following the coarse-to-fine manners. By simulating this human’s behaviour, we develop two versions of C2FPS-ML for two different scenarios: one is natural object dataset and another one is other kinds of dataset (e.g., handwritten character dataset). For natural object dataset scenario, we propose to exploit the potential hierarchical semantics of the unlabeled auxiliary dataset to build a tree-like structure of visual concepts. For another scenario, progressive pseudo supervision is obtained by forming clusters in different similarity aspects and is represented by a pyramid-like structure. The obtained structure is applied as the supervision to construct meta-tasks in meta-training stage, and prior knowledge from the unlabeled auxiliary dataset is learned from the coarse-grained level to the fine-grained level. The proposed method sets the new state of the art on the gold-standard miniImageNet and achieves remarkable results on Omniglot while simultaneously increases efficiency.

see all

Series: Pattern recognition
ISSN: 0031-3203
ISSN-E: 1873-5142
ISSN-L: 0031-3203
Volume: 122
Article number: 108296
DOI: 10.1016/j.patcog.2021.108296
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
Funding: The work of Yawen Cui was partially supported by China Scholarship Council (CSC) under grant 201903170129. This work was partially supported by the Academy of Finland under grant 331883, the National Natural Science Foundation of China under Grant 61872379, 71701205 and 62022091.
Academy of Finland Grant Number: 331883
Detailed Information: 331883 (Academy of Finland Funding decision)
Copyright information: © 2022. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http:/