ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Generalized semi-supervised class incremental learning in presence of outliers

Kalla, J and Punia, P and Dutta, T and Biswas, S (2023) Generalized semi-supervised class incremental learning in presence of outliers. In: Multimedia Tools and Applications .

[img] PDF
mul_too_app_2023.pdf - Published Version
Restricted to Registered users only

Download (1MB) | Request a copy
Official URL: https://doi.org/10.1007/s11042-023-15975-w


In this work, we focus on addressing the challenging real-world problem of generalized semi-supervised class-incremental learning (GSS-CIL), which has received relatively little attention in the research community. This involves having a limited number of labeled samples from the new classes at each incremental step, along with a large number of unlabeled samples from these new-classes, previously seen (older-tasks) or completely unseen classes (outliers). Our contributions are three-fold: Firstly, we provide a comprehensive definition and motivation of the GSS-CIL protocol and evaluate the performance of existing state-of-the-art class incremental learning (CIL) methods under this protocol. Secondly, we propose a simple yet effective framework called the Expert-Suggested Pseudo-labelling Network (ESPN) to tackle the GSS-CIL problem by leveraging the information contained in the unlabeled training data. Finally, we use task-wise Harmonic Mean as an additional evaluation metric to capture performance on both new and older tasks. We conduct extensive experiments on three standard large-scale datasets to demonstrate the effectiveness of our proposed ESPN approach, which can serve as a strong baseline for future research in this challenging real-world scenario.

Item Type: Journal Article
Publication: Multimedia Tools and Applications
Publisher: Springer
Additional Information: The copyright for this article belongs to the Springer.
Keywords: Class-incremental learning; Selective pseudo-labelling; Semi-supervised learning.
Department/Centre: Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited: 24 Jul 2023 05:33
Last Modified: 24 Jul 2023 05:33
URI: https://eprints.iisc.ac.in/id/eprint/82614

Actions (login required)

View Item View Item