Towards Label-Free Few-Shot Learning: How Far Can We Go?

Bharti, Aditya and Balasubramanian, Vineeth N and Jawahar, C. V. (2022) Towards Label-Free Few-Shot Learning: How Far Can We Go? In: 6th International Conference on Computer Vision and Image Processing, CVIP 2021, 3 December 2021 through 5 December 2021, Virtual, Online.

Full text not available from this repository. (Request a copy)


Few-shot learners aim to recognize new categories given only a small number of training samples. The core challenge is to avoid overfitting to the limited data while ensuring good generalization to novel classes. Existing literature makes use of vast amounts of annotated data by simply shifting the label requirement from novel classes to base classes. Since data annotation is time-consuming and costly, reducing the label requirement even further is an important goal. To that end, our paper presents a more challenging few-shot setting with almost no class label access. By leveraging self-supervision to learn image representations and similarity for classification at test time, we achieve competitive baselines while using almost zero (0–5) class labels. Compared to existing state-of-the-art approaches which use 60,000 labels, this is a four orders of magnitude (10,000 times) difference. This work is a step towards developing few-shot learning methods that do not depend on annotated data. Our code is publicly released at (This work was supported by the IMPRINT program.) © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Balasubramanian, Vineeth NUNSPECIFIED
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Deep learning; Few shot; Self-supervised
Subjects: Computer science
Divisions: Department of Computer Science & Engineering
Depositing User: . LibTrainee 2021
Date Deposited: 06 Aug 2022 06:49
Last Modified: 06 Aug 2022 06:49
Publisher URL:
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 10113 Statistics for this ePrint Item