Related papers: Adversarial Feature Augmentation and Normalization…
Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several…
Existing fine-grained image retrieval (FGIR) methods predominantly rely on supervision from predefined categories to learn discriminative representations for retrieving fine-grained objects. However, they inadvertently introduce…
Despite data augmentation being a de facto technique for boosting the performance of deep neural networks, little attention has been paid to developing augmentation strategies for generative adversarial networks (GANs). To this end, we…
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks, where small perturbations intentionally added to the original inputs can fool the classifier. In this paper, we propose a defense method, Featurized…
Anomaly detection is a fundamental problem in computer vision area with many real-world applications. Given a wide range of images belonging to the normal class, emerging from some distribution, the objective of this task is to construct…
Adding perturbations to images can mislead classification models to produce incorrect results. Recently, researchers exploited adversarial perturbations to protect image privacy from retrieval by intelligent models. However, adding…
Recent studies have shown that Convolutional Neural Networks (CNNs) are vulnerable to a small perturbation of input called "adversarial examples". In this work, we propose a new feedforward CNN that improves robustness in the presence of…
Self-supervised contrastive learning heavily relies on the view variance brought by data augmentation, so that it can learn a view-invariant pre-trained representation. Beyond increasing the view variance for contrast, this work focuses on…
In this paper, we propose a principled Perceptual Adversarial Networks (PAN) for image-to-image transformation tasks. Unlike existing application-specific algorithms, PAN provides a generic framework of learning mapping relationship between…
Random data augmentation is a critical technique to avoid overfitting in training deep neural network models. However, data augmentation and network training are usually treated as two isolated processes, limiting the effectiveness of…
Compared with traditional machine learning models, deep neural networks perform better, especially in image classification tasks. However, they are vulnerable to adversarial examples. Adding small perturbations on examples causes a…
As humans, we inherently perceive images based on their predominant features, and ignore noise embedded within lower bit planes. On the contrary, Deep Neural Networks are known to confidently misclassify images corrupted with meticulously…
As designers of artificial intelligence try to outwit hackers, both sides continue to hone in on AI's inherent vulnerabilities. Designed and trained from certain statistical distributions of data, AI's deep neural networks (DNNs) remain…
In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping,…
Deep Learning methods have become state-of-the-art for solving tasks such as Face Recognition (FR). Unfortunately, despite their success, it has been pointed out that these learning models are exposed to adversarial inputs - images to which…
This paper addresses 2 challenging tasks: improving the quality of low resolution facial images and accurately locating the facial landmarks on such poor resolution images. To this end, we make the following 5 contributions: (a) we propose…
Adding perturbations via utilizing auxiliary gradient information or discarding existing details of the benign images are two common approaches for generating adversarial examples. Though visual imperceptibility is the desired property of…
The performance of a convolutional neural network (CNN) based face recognition model largely relies on the richness of labelled training data. Collecting a training set with large variations of a face identity under different poses and…
We present a continual learning approach for generative adversarial networks (GANs), by designing and leveraging parameter-efficient feature map transformations. Our approach is based on learning a set of global and task-specific…
In asymmetric retrieval systems, models with different capacities are deployed on platforms with different computational and storage resources. Despite the great progress, existing approaches still suffer from a dilemma between retrieval…