Curriculum By Smoothing
arXiv:2003.01367
Abstract
Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. Moreover, recent work in Generative Adversarial Networks (GANs) has highlighted the importance of learning by progressively increasing the difficulty of a learning task [26]. When learning a network from scratch, the information propagated within the network during the earlier stages of training can contain distortion artifacts due to noise which can be detrimental to training. In this paper, we propose an elegant curriculum based scheme that smoothes the feature embedding of a CNN using anti-aliasing or low-pass filters. We propose to augment the train-ing of CNNs by controlling the amount of high frequency information propagated within the CNNs as training progresses, by convolving the output of a CNN feature map of each layer with a Gaussian kernel. By decreasing the variance of the Gaussian kernel, we gradually increase the amount of high-frequency information available within the network for inference. As the amount of information in the feature maps increases during training, the network is able to progressively learn better representations of the data. Our proposed augmented training scheme significantly improves the performance of CNNs on various vision tasks without either adding additional trainable parameters or an auxiliary regularization objective. The generality of our method is demonstrated through empirical performance gains in CNN architectures across four different tasks: transfer learning, cross-task transfer learning, and generative models.
arXiv commentNeurIPS 2020 (Spotlight)
References in corpus (17)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Instance Normalization: The Missing Ingredient for Fast Stylization
- Wide Residual Networks
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks
- Do ImageNet Classifiers Generalize to ImageNet?
- Making Convolutional Networks Shift-Invariant Again
- What makes ImageNet good for transfer learning?
- Learning to Execute
- Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
- Wasserstein Auto-Encoders
- Reverse Curriculum Generation for Reinforcement Learning
- Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play
- Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network
- Avoiding Latent Variable Collapse With Generative Skip Models