Learning Structure and Strength of CNN Filters for Small Sample Size Training

TL;DR

This paper introduces SSF-CNN, a novel approach that learns filter structure and strength to enable effective training of CNNs with small datasets, achieving high accuracy and reducing parameters.

Contribution

The paper proposes a new CNN training method that initializes filter structure via dictionary learning and learns filter strength from limited data, improving small sample performance.

Findings

SSF-CNN reduces parameter count significantly.

Achieves high accuracy on small datasets like newborn face recognition.

Outperforms existing methods with at least 10% accuracy improvement.

Abstract

Convolutional Neural Networks have provided state-of-the-art results in several computer vision problems. However, due to a large number of parameters in CNNs, they require a large number of training samples which is a limiting factor for small sample size problems. To address this limitation, we propose SSF-CNN which focuses on learning the structure and strength of filters. The structure of the filter is initialized using a dictionary-based filter learning algorithm and the strength of the filter is learned using the small sample training data. The architecture provides the flexibility of training with both small and large training databases and yields good accuracies even with small size training data. The effectiveness of the algorithm is first demonstrated on MNIST, CIFAR10, and NORB databases, with a varying number of training samples. The results show that SSF-CNN significantly reduces the number of parameters required for training while providing high accuracies the test databases. On small sample size problems such as newborn face recognition and Omniglot, it yields state-of-the-art results. Specifically, on the IIITD Newborn Face Database, the results demonstrate improvement in rank-1 identification accuracy by at least 10%.