GMM-IL: Image Classification using Incrementally Learnt, Independent Probabilistic Models for Small Sample Sizes
This addresses the challenge of incremental learning in image classification for scenarios with small or imbalanced datasets, though it is an incremental improvement over existing methods.
The paper tackles the problem of catastrophic forgetting in deep learning classifiers when incrementally learning new classes, by introducing a two-stage architecture that combines visual feature learning with independent Gaussian Mixture Models for each class. The result is improved accuracy for sample sizes smaller than 12 and better weighted F1 scores for imbalanced classes, with no forgetting issues and no need for old training data.
Current deep learning classifiers, carry out supervised learning and store class discriminatory information in a set of shared network weights. These weights cannot be easily altered to incrementally learn additional classes, since the classification weights all require retraining to prevent old class information from being lost and also require the previous training data to be present. We present a novel two stage architecture which couples visual feature learning with probabilistic models to represent each class in the form of a Gaussian Mixture Model. By using these independent class representations within our classifier, 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. When learning new classes our classifier exhibits no catastrophic forgetting issues and only requires the new classes' training images to be present. This enables a database of growing classes over time which can be visually indexed and reasoned over.