Unseen Classes at a Later Time? No Problem

Kuchibhotla, Hari Chandana and Malagi, Sumitra S and Chandhok, Shivam and Balasubramanian, Vineeth N (2022) Unseen Classes at a Later Time? No Problem. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, 19 - 24 June 2022, New Orleans.

Text
Proceedings_of_the_IEEE_Computer_Society_Conference.pdf - Published Version
Available under License Creative Commons Attribution.
Download (7MB)

Abstract

Recent progress towards learning from limited supervision has encouraged efforts towards designing models that can recognize novel classes at test time (generalized zero-shot learning or GZSL). GZSL approaches assume knowledge of all classes, with or without labeled data, beforehand. However, practical scenarios demand models that are adaptable and can handle dynamic addition of new seen and unseen classes on the fly (i.e continual generalized zero-shot learning or CGZSL). One solution is to sequentially retrain and reuse conventional GZSL methods, however, such an approach suffers from catastrophic forgetting leading to suboptimal generalization performance. A few recent efforts towards tackling CGZSL have been limited by difference in settings, practicality, data splits and protocols followed - inhibiting fair comparison and a clear direction forward. Motivated from these observations, in this work, we firstly consolidate the different CGZSL setting variants and propose a new Online-CGZSL setting which is more practical and flexible. Secondly, we introduce a unified feature-generative framework for CGZSL that leverages bi-directional incremental alignment to dynamically adapt to addition of new classes, with or without labeled data, that arrive over time in any of these CGZSL settings. Our comprehensive experiments and analysis on five benchmark datasets and comparison with baselines show that our approach consistently outperforms existing methods, especially on the more practical Online setting. © 2022 IEEE.

[error in script]

IITH Creators:

IITH Creators	ORCiD
Balasubramanian, Vineeth N	UNSPECIFIED

Item Type:

Conference or Workshop Item (Paper)

Additional Information:

Acknowledgements. This work has been partly supported by the funding received from DST through the IMPRINT and ICPS programs. Hari Chandana Kuchibhotla would like to thank MoE for the PMRF fellowship support. We thank the anonymous reviewers for their valuable feedback that improved the presentation of this paper.

Uncontrolled Keywords:

Others; Self-& semi-& meta- & unsupervised learning; Transfer/low-shot/long-tail learning

Subjects:

Computer science

Divisions:

Department of Computer Science & Engineering

Depositing User:

. LibTrainee 2021

Date Deposited:

23 Nov 2022 11:34

Last Modified:

23 Nov 2022 11:34