Exploiting the Full Capacity of Deep Neural Networks while Avoiding Overfitting by Targeted Sparsity Regularization
This addresses overfitting for practitioners training deep models on limited data, offering a novel regularization method with incremental improvements over existing techniques.
The paper tackles overfitting in deep neural networks on small datasets by using activation sparsity as an indicator, proposing targeted sparsity regularization to counteract it layer-by-layer, resulting in significant performance gains in image classification that outperform dropout and batch normalization.
Overfitting is one of the most common problems when training deep neural networks on comparatively small datasets. Here, we demonstrate that neural network activation sparsity is a reliable indicator for overfitting which we utilize to propose novel targeted sparsity visualization and regularization strategies. Based on these strategies we are able to understand and counteract overfitting caused by activation sparsity and filter correlation in a targeted layer-by-layer manner. Our results demonstrate that targeted sparsity regularization can efficiently be used to regularize well-known datasets and architectures with a significant increase in image classification performance while outperforming both dropout and batch normalization. Ultimately, our study reveals novel insights into the contradicting concepts of activation sparsity and network capacity by demonstrating that targeted sparsity regularization enables salient and discriminative feature learning while exploiting the full capacity of deep models without suffering from overfitting, even when trained excessively.