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

arXiv: https://arxiv.org/abs/1803.11405 · HTML: https://mlsanity.com/paper/1803.11405/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2018.

## Built on by (most cited first, 8 of 8)

- [Image Classification with Small Datasets: Overview and Benchmark](https://mlsanity.com/paper/2212.12478/) (2022)
- [CeCNN: Copula-enhanced convolutional neural networks in joint prediction of refraction error and axial length based on ultra-widefield fundus images](https://mlsanity.com/paper/2311.03967/) (2023)
- [Analyzing and Mitigating Bias for Vulnerable Classes: Towards Balanced Representation in Dataset](https://mlsanity.com/paper/2401.10397/) (2024)
- [No Data Augmentation? Alternative Regularizations for Effective Training on Small Datasets](https://mlsanity.com/paper/2309.01694/) (2023)
- [Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions](https://mlsanity.com/paper/2103.15383/) (2021)
- [How Can Incentives and Cut Layer Selection Influence Data Contribution in Split Federated Learning?](https://mlsanity.com/paper/2412.07813/) (2024)
- [MetaCLBench: Meta Continual Learning Benchmark on Resource-Constrained Edge Devices](https://mlsanity.com/paper/2504.00174/) (2025)
- [Interpretable Machine Learning for Antepartum Prediction of Pregnancy-Associated Thrombotic Microangiopathy Using Routine Longitudinal Laboratory Data](https://mlsanity.com/paper/2605.13786/) (2026)

## Abstract (arXiv)

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%.