|Appears in Collections:||Computing Science and Mathematics Journal Articles|
|Peer Review Status:||Refereed|
|Title:||GMM-IL: Image Classification Using Incrementally Learnt, Independent Probabilistic Models for Small Sample Sizes|
Gaussian mixture model
|Citation:||Johnston P, Nogueira K & Swingler K (2023) GMM-IL: Image Classification Using Incrementally Learnt, Independent Probabilistic Models for Small Sample Sizes. <i>IEEE Access</i>, 11, pp. 25492-25501. https://doi.org/10.1109/access.2023.3255795|
|Abstract:||When deep-learning classifiers try to learn new classes through supervised learning, they exhibit catastrophic forgetting issues. In this paper we propose the Gaussian Mixture Model - Incremental Learner (GMM-IL), a novel two-stage architecture that couples unsupervised visual feature learning with supervised probabilistic models to represent each class. The key novelty of GMM-IL is that each class is learnt independently of the other classes. New classes can be incrementally learnt using a small set of annotated images with no requirement to relearn data from existing classes. This enables the incremental addition of classes to a model, that can be indexed by visual features and reasoned over based on perception. Using Gaussian Mixture Models to represent the independent classes, we outperform a benchmark of an equivalent network with a Softmax head, obtaining increased accuracy for sample sizes smaller than 12 and increased weighted F1 score for 3 imbalanced class profiles in that sample range. This novel method enables new classes to be added to a system with only access to a few annotated images of the new class.|
|Rights:||This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/|
|GMM-IL_Image_Classification_Using_Incrementally_Learnt_Independent_Probabilistic_Models_for_Small_Sample_Sizes.pdf||Fulltext - Published Version||1.24 MB||Adobe PDF||View/Open|
This item is protected by original copyright
A file in this item is licensed under a Creative Commons License
Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
The metadata of the records in the Repository are available under the CC0 public domain dedication: No Rights Reserved https://creativecommons.org/publicdomain/zero/1.0/
If you believe that any material held in STORRE infringes copyright, please contact email@example.com providing details and we will remove the Work from public display in STORRE and investigate your claim.