Related papers: AugMax: Adversarial Composition of Random Augmenta…
Data augmentation (DA) has been widely used to improve the generalization of deep neural networks. While existing DA methods have proven effective, they often rely on augmentation operations with random magnitudes to each sample. However,…
Image clustering has recently attracted significant attention due to the increased availability of unlabelled datasets. The efficiency of traditional clustering algorithms heavily depends on the distance functions used and the…
Adversarial training is an effective learning technique to improve the robustness of deep neural networks. In this study, the influence of adversarial training on deep learning models in terms of fairness, robustness, and generalization is…
Convolutional neural networks (CNN) are capable of learning robust representation with different regularization methods and activations as convolutional layers are spatially correlated. Based on this property, a large variety of regional…
Adversarial examples are augmented data points generated by imperceptible perturbation of input samples. They have recently drawn much attention with the machine learning and data mining community. Being difficult to distinguish from real…
The core of the general recommender systems lies in learning high-quality embedding representations of users and items to investigate their positional relations in the feature space. Unfortunately, data sparsity caused by…
Mixup data augmentation approaches have been applied for various tasks of deep learning to improve the generalization ability of deep neural networks. Some existing approaches CutMix, SaliencyMix, etc. randomly replace a patch in one image…
Even nowadays, where Deep Learning (DL) has achieved state-of-the-art performance in a wide range of research domains, accelerating training and building robust DL models remains a challenging task. To this end, generations of researchers…
Adversarial attacks have been shown to be highly effective at degrading the performance of deep neural networks (DNNs). The most prominent defense is adversarial training, a method for learning a robust model. Nevertheless, adversarial…
Domain generalization aims to develop models that are robust to distribution shifts. Existing methods focus on learning invariance across domains to enhance model robustness, and data augmentation has been widely used to learn invariant…
Data augmentation has shown its effectiveness in resolving the data-hungry problem and improving model's generalization ability. However, the quality of augmented data can be varied, especially compared with the raw/original data. To boost…
Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in…
In communication systems, there are many tasks, like modulation recognition, which rely on Deep Neural Networks (DNNs) models. However, these models have been shown to be susceptible to adversarial perturbations, namely imperceptible…
Data augmentation is an effective technique to improve the generalization of deep neural networks. Recently, AutoAugment proposed a well-designed search space and a search algorithm that automatically finds augmentation policies in a…
With the rapid development of deep learning, automatic modulation recognition (AMR), as an important task in cognitive radio, has gradually transformed from traditional feature extraction and classification to automatic classification by…
Training of Generative Adversarial Networks (GANs) is notoriously fragile, requiring to maintain a careful balance between the generator and the discriminator in order to perform well. To mitigate this issue we introduce a new…
Machine Unlearning (MU) aims to remove the influence of specific data from a trained model while preserving its performance on the remaining data. Although a few works suggest connections between memorisation and augmentation, the role of…
Deep neural networks (DNNs) provide state-of-the-art results on various tasks and are widely used in real world applications. However, it was discovered that machine learning models, including the best performing DNNs, suffer from a…
Data augmentation methods are indispensable heuristics to boost the performance of deep neural networks, especially in image recognition tasks. Recently, several studies have shown that augmentation strategies found by search algorithms…
Deep models, while being extremely versatile and accurate, are vulnerable to adversarial attacks: slight perturbations that are imperceptible to humans can completely flip the prediction of deep models. Many attack and defense mechanisms…