Robust Learning with Frequency Domain Regularization

Abstract

Convolution neural networks have achieved remarkable performance in many tasks of computing vision. However, CNN tends to bias to low frequency components. They prioritize capturing low frequency patterns which lead them fail when suffering from application scenario transformation. While adversarial example implies the model is very sensitive to high frequency perturbations. In this paper, we introduce a new regularization method by constraining the frequency spectra of the filter of the model. Different from band-limit training, our method considers the valid frequency range probably entangles in different layers rather than continuous and trains the valid frequency range end-to-end by backpropagation. We demonstrate the effectiveness of our regularization by (1) defensing to adversarial perturbations; (2) reducing the generalization gap in different architecture; (3) improving the generalization ability in transfer learning scenario without fine-tune.

References in corpus (10)

• YOLOv3: An Incremental Improvement
• AutoAugment: Learning Augmentation Policies from Data
• DropBlock: A regularization method for convolutional networks
• Measuring the tendency of CNNs to Learn Surface Statistical Regularities
• Why do deep convolutional networks generalize so poorly to small image transformations?
• Generalizable Adversarial Training via Spectral Normalization
• Robust Learning with Jacobian Regularization
• Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision
• Exploring Categorical Regularization for Domain Adaptive Object Detection
• Band-limited Training and Inference for Convolutional Neural Networks