Log In Sign Up

Group-wise Inhibition based Feature Regularization for Robust Classification

by   Haozhe Liu, et al.

The vanilla convolutional neural network (CNN) is vulnerable to images with small variations (e.g. corrupted and adversarial samples). One of the possible reasons is that CNN pays more attention to the most discriminative regions, but ignores the auxiliary features, leading to the lack of feature diversity. In our method , we propose to dynamically suppress significant activation values of vanilla CNN by group-wise inhibition, but not fix or randomly handle them when training. Then, the feature maps with different activation distribution are processed separately due to the independence of features. Vanilla CNN is finally guided to learn more rich discriminative features hierarchically for robust classification according to proposed regularization. The proposed method is able to achieve a significant gain of robustness over 15 state-of-the-art. We also show that the proposed regularization method complements other defense paradigms, such as adversarial training, to further improve the robustness.


page 2

page 3

page 6

page 7


PatchShuffle Regularization

This paper focuses on regularizing the training of the convolutional neu...

Reveal of Vision Transformers Robustness against Adversarial Attacks

Attention-based networks have achieved state-of-the-art performance in m...

Robust Representation via Dynamic Feature Aggregation

Deep convolutional neural network (CNN) based models are vulnerable to t...

Feature prioritization and regularization improve standard accuracy and adversarial robustness

Adversarial training has been successfully applied to build robust model...

Towards Robust 2D Convolution for Reliable Visual Recognition

2D convolution (Conv2d), which is responsible for extracting features fr...

Robust Classification with Convolutional Prototype Learning

Convolutional neural networks (CNNs) have been widely used for image cla...

Regularizing Neural Network Training via Identity-wise Discriminative Feature Suppression

It is well-known that a deep neural network has a strong fitting capabil...