Structured Output Regularization: a framework for few-shot transfer learning
This addresses the challenge of adapting pre-trained models to domain-specific features with minimal data, particularly in medical imaging, though it appears incremental as it builds on existing regularization techniques.
The paper tackled the problem of overfitting and limited adaptation in few-shot transfer learning by proposing Structured Output Regularization (SOR), a framework that freezes internal network structures and uses group lasso and L1 penalties, achieving competitive results on three few-shot medical imaging classification tasks.
Traditional transfer learning typically reuses large pre-trained networks by freezing some of their weights and adding task-specific layers. While this approach is computationally efficient, it limits the model's ability to adapt to domain-specific features and can still lead to overfitting with very limited data. To address these limitations, we propose Structured Output Regularization (SOR), a simple yet effective framework that freezes the internal network structures (e.g., convolutional filters) while using a combination of group lasso and $L_1$ penalties. This framework tailors the model to specific data with minimal additional parameters and is easily applicable to various network components, such as convolutional filters or various blocks in neural networks enabling broad applicability for transfer learning tasks. We evaluate SOR on three few shot medical imaging classification tasks and we achieve competitive results using DenseNet121, and EfficientNetB4 bases compared to established benchmarks.