We propose a new regularization method to alleviate over-fitting in deep neural networks.

We propose a new regularization method to alleviate over-fitting in deep neural networks. The key idea is utilizing randomly transformed training samples to regularize a set of sub-networks, which are originated by sampling the width of the original network, in the training process. As such, the proposed method introduces self-guided disturbances to the raw gradients of the network and therefore is termed as Gradient Augmentation (GradAug). We demonstrate that GradAug can help the network learn well-generalized and more diverse representations. Moreover, it is easy to implement and can be applied to various structures and applications. GradAug improves ResNet-50 to 78.79% on ImageNet classification, which is a new state-of-the-art accuracy. By combining with CutMix, it further boosts the performance to 79.67%, which outperforms an ensemble of advanced training tricks. The generalization ability is evaluated on COCO object detection and instance segmentation where GradAug significantly surpasses other state-of-the-art methods. GradAug is also robust to image distortions and FGSM adversarial attacks and is highly effective in low data regimes.

The supplementary material includes the following items.

We sincerely thank reviewers for their insightful feedback! We address reviewer com ments below. Table 1 shows a comparison on ImageNet. So the training cost of our GradAug is comparable with SOT A methods. Analyzing the effect of different sampling strategies is interesting and we will certainly explore it in future work.

Summary and Contributions: After rebuttal and discussion with other reviewers I have updated my score. However, I do point out several concerns of mine which the authors could consider further validation for: It's good that the authors performed the time/memory comparison in the rebuttal as that was a significant concern of mine. My concerns mostly revolve around what other techniques should we compare this against? Given that this algorithm takes 3-4x the time with comparison to the baseline, I could for example: 1: Train a much larger network and then use compression techniques to slim it to the same size. Mixup which is still 70% faster.

All four reviewers support acceptance. They found that the claims are well supported by the strong experiments.

We propose a new regularization method to alleviate over-fitting in deep neural networks. The key idea is utilizing randomly transformed training samples to regularize a set of sub-networks, which are originated by sampling the width of the original network, in the training process. As such, the proposed method introduces self-guided disturbances to the raw gradients of the network and therefore is termed as Gradient Augmentation (GradAug). We demonstrate that GradAug can help the network learn well-generalized and more diverse representations. Moreover, it is easy to implement and can be applied to various structures and applications. GradAug improves ResNet-50 to 78.79% on ImageNet classification, which is a new state-of-the-art accuracy.

We propose a new regularization method to alleviate over-fitting in deep neural networks. The key idea is utilizing randomly transformed training samples to regularize a set of sub-networks, which are originated by sampling the width of the original network, in the training process. As such, the proposed method introduces self-guided disturbances to the raw gradients of the network and therefore is termed as Gradient Augmentation (GradAug). We demonstrate that GradAug can help the network learn well-generalized and more diverse representations. Moreover, it is easy to implement and can be applied to various structures and applications. GradAug improves ResNet-50 to 78.79% on ImageNet classification, which is a new state-of-the-art accuracy.