Related papers: NSA: Naturalistic Support Artifact to Boost Networ…
Recent advances in machine learning have greatly benefited object detection and 6D pose estimation. However, textureless and metallic objects still pose a significant challenge due to few visual cues and the texture bias of CNNs. To address…
Deep learning has become an integral part of various computer vision systems in recent years due to its outstanding achievements for object recognition, facial recognition, and scene understanding. However, deep neural networks (DNNs) are…
Deep convolutional neural networks (DCNNs) have revolutionized computer vision and are often advocated as good models of the human visual system. However, there are currently many shortcomings of DCNNs, which preclude them as a model of…
One major factor impeding more widespread adoption of deep neural networks (DNNs) is their lack of robustness, which is essential for safety-critical applications such as autonomous driving. This has motivated much recent work on…
Light-based adversarial attacks use spatial augmented reality (SAR) techniques to fool image classifiers by altering the physical light condition with a controllable light source, e.g., a projector. Compared with physical attacks that place…
Face swapping manipulations in video streams represents an increasing threat in remote video communications, due to advances in automated and real-time tools. Recent literature proposes to characterize and exploit visual artifacts…
Human visual systems are robust to a wide range of image transformations that are challenging for artificial networks. We present the first study of image model robustness to the minute transformations found across video frames, which we…
Image super-resolution (SR) with generative adversarial networks (GAN) has achieved great success in restoring realistic details. However, it is notorious that GAN-based SR models will inevitably produce unpleasant and undesirable…
Solving inverse problems continues to be a central challenge in computer vision. Existing techniques either explicitly construct an inverse mapping using prior knowledge about the corruption, or learn the inverse directly using a large…
Despite the effectiveness in improving the robustness of neural networks, adversarial training has suffered from the natural accuracy degradation problem, i.e., accuracy on natural samples has reduced significantly. In this study, we reveal…
In the last few years, the artifact patterns in fake images synthesized by different generative models have been inconsistent, leading to the failure of previous research that relied on spotting subtle differences between real and fake. In…
Surface inspection systems are an important application domain for computer vision, as they are used for defect detection and classification in the manufacturing industry. Existing systems use hand-crafted features which require extensive…
The problem of adversarial examples has shown that modern Neural Network (NN) models could be rather fragile. Among the more established techniques to solve the problem, one is to require the model to be {\it $\epsilon$-adversarially…
Model explanations such as saliency maps can improve user trust in AI by highlighting important features for a prediction. However, these become distorted and misleading when explaining predictions of images that are subject to systematic…
The usage of Artificial Intelligence (AI) systems has increased exponentially, thanks to their ability to reduce the amount of data to be analyzed, the user efforts and preserving a high rate of accuracy. However, introducing this new…
Learning-based image compression methods have improved in recent years and started to outperform traditional codecs. However, neural-network approaches can unexpectedly introduce visual artifacts in some images. We therefore propose methods…
Generative adversarial networks (GANs) offer an effective solution to the image-to-image translation problem, thereby allowing for new possibilities in medical imaging. They can translate images from one imaging modality to another at a low…
Thanks to recent advances in deep neural networks (DNNs), face recognition systems have become highly accurate in classifying a large number of face images. However, recent studies have found that DNNs could be vulnerable to adversarial…
Invariance to a broad array of image corruptions, such as warping, noise, or color shifts, is an important aspect of building robust models in computer vision. Recently, several new data augmentations have been proposed that significantly…
Anomaly detection is a critical challenge across various research domains, aiming to identify instances that deviate from normal data distributions. This paper explores the application of Generative Adversarial Networks (GANs) in fraud…