# Group-wise Inhibition based Feature Regularization for Robust Classification

arXiv: https://arxiv.org/abs/2103.02152 · HTML: https://mlsanity.com/paper/2103.02152/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 3 Mar 2021.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Feature Denoising for Improving Adversarial Robustness](https://mlsanity.com/paper/1812.03411/) (2018)
- [Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2004.04581/) (2020)
- [Adversarial Examples Improve Image Recognition](https://mlsanity.com/paper/1911.09665/) (2019)
- [Efficient Object Localization Using Convolutional Networks](https://mlsanity.com/paper/1411.4280/) (2014)
- [Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach](https://mlsanity.com/paper/1703.08448/) (2017)
- [Attention-based Dropout Layer for Weakly Supervised Object Localization](https://mlsanity.com/paper/1908.10028/) (2019)
- [Self-Erasing Network for Integral Object Attention](https://mlsanity.com/paper/1810.09821/) (2018)
- [Wavelet Integrated CNNs for Noise-Robust Image Classification](https://mlsanity.com/paper/2005.03337/) (2020)
- [Efficient Adversarial Training with Transferable Adversarial Examples](https://mlsanity.com/paper/1912.11969/) (2019)
- [Training Group Orthogonal Neural Networks with Privileged Information](https://mlsanity.com/paper/1701.06772/) (2017)
- [Generative Latent Implicit Conditional Optimization when Learning from Small Sample](https://mlsanity.com/paper/2003.14297/) (2020)
- [Robust Assessment of Real-World Adversarial Examples](https://mlsanity.com/paper/1911.10435/) (2019)

## Built on by (most cited first, 11 of 11)

- [Scene Consistency Representation Learning for Video Scene Segmentation](https://mlsanity.com/paper/2205.05487/) (2022)
- [Fingerprint Presentation Attack Detection by Channel-wise Feature Denoising](https://mlsanity.com/paper/2111.07620/) (2021)
- [Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Survey](https://mlsanity.com/paper/2303.06302/) (2023)
- [Manifold-preserved GANs](https://mlsanity.com/paper/2109.08955/) (2021)
- [Robust Representation via Dynamic Feature Aggregation](https://mlsanity.com/paper/2205.07466/) (2022)
- [Activation Template Matching Loss for Explainable Face Recognition](https://mlsanity.com/paper/2207.02179/) (2022)
- [Dynamically Masked Discriminator for Generative Adversarial Networks](https://mlsanity.com/paper/2306.07716/) (2023)
- [PushPull-Net: Inhibition-driven ResNet robust to image corruptions](https://mlsanity.com/paper/2408.04077/) (2024)
- [Decoupled Mixup for Generalized Visual Recognition](https://mlsanity.com/paper/2210.14783/) (2022)
- [Improving GAN Training via Feature Space Shrinkage](https://mlsanity.com/paper/2303.01559/) (2023)
- [A Benchmark for Weakly Semi-Supervised Abnormality Localization in Chest X-Rays](https://mlsanity.com/paper/2209.01988/) (2022)

## Abstract (arXiv)

The convolutional neural network (CNN) is vulnerable to degraded images with even very 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 when learning, leading to the lack of feature diversity for final judgment. In our method, we propose to dynamically suppress significant activation values of CNN by group-wise inhibition, but not fixedly or randomly handle them when training. The feature maps with different activation distribution are then processed separately to take the feature independence into account. CNN is finally guided to learn richer discriminative features hierarchically for robust classification according to the proposed regularization. Our method is comprehensively evaluated under multiple settings, including classification against corruptions, adversarial attacks and low data regime. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both robustness and generalization performances, when compared with the state-of-the-art methods. Code is available at https://github.com/LinusWu/TENET_Training.