<ul><li>Overfitting is a common issue in Machine Learning models, even among state-of-the-art models, leading to reduced generalization and a significant performance gap between training and testing sets.</li><li>To address overfitting, various techniques like dropout, data augmentation, and weight decay are used for regularization.</li><li>A new data augmentation method called Relevance-driven Input Dropout (RelDrop) is proposed, which selectively occludes the most relevant regions of the input to improve model generalization through informed regularization.</li><li>Experiments on benchmark datasets show that RelDrop enhances robustness towards occlusion, encourages models to use more features in prediction, and improves generalization performance during inference.</li></ul>

Relevance-driven Input Dropout: an Explanation-guided Regularization Technique

Discover more