Related papers: Transferring Styles for Reduced Texture Bias and I…
Convolutional Neural Networks (CNNs) have become the state-of-the-art method to learn from image data. However, recent research shows that they may include a texture and colour bias in their representation, contrary to the intuition that…
Recent research has investigated the shape and texture biases of pre-trained deep neural networks (DNNs) in image classification. Those works test how much a trained DNN relies on specific image cues like texture. The present study shifts…
We introduce style augmentation, a new form of data augmentation based on random style transfer, for improving the robustness of convolutional neural networks (CNN) over both classification and regression based tasks. During training, our…
Convolutional neural networks (CNNs) learn to extract representations of complex features, such as object shapes and textures to solve image recognition tasks. Recent work indicates that CNNs trained on ImageNet are biased towards features…
Previous works studied how deep neural networks (DNNs) perceive image content in terms of their biases towards different image cues, such as texture and shape. Previous methods to measure shape and texture biases are typically…
The success of training deep Convolutional Neural Networks (CNNs) heavily depends on a significant amount of labelled data. Recent research has found that neural style transfer algorithms can apply the artistic style of one image to another…
Deep Neural Networks (DNNs)-based semantic segmentation models trained on a source domain often struggle to generalize to unseen target domains, i.e., a domain gap problem. Texture often contributes to the domain gap, making DNNs vulnerable…
Convolutional neural networks (CNNs) have proven highly effective at image synthesis and style transfer. For most users, however, using them as tools can be a challenging task due to their unpredictable behavior that goes against common…
Convolutional neural networks (CNNs) for image processing tend to focus on localized texture patterns, commonly referred to as texture bias. While most of the previous works in the literature focus on the task of image classification, we go…
Deep Neural Networks (DNNs) suffer from the performance degradation when image appearance shift occurs, especially in ultrasound (US) image segmentation. In this paper, we propose a novel and intuitive framework to remove the appearance…
State-of-the-art parametric and non-parametric style transfer approaches are prone to either distorted local style patterns due to global statistics alignment, or unpleasing artifacts resulting from patch mismatching. In this paper, we…
Currently, style augmentation is capturing attention due to convolutional neural networks (CNN) being strongly biased toward recognizing textures rather than shapes. Most existing styling methods either perform a low-fidelity style transfer…
This paper presents an automatic image synthesis method to transfer the style of an example image to a content image. When standard neural style transfer approaches are used, the textures and colours in different semantic regions of the…
Convolutional Neural Networks (CNNs) often fail to maintain their performance when they confront new test domains, which is known as the problem of domain shift. Recent studies suggest that one of the main causes of this problem is CNNs'…
Deep neural networks are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on clean inputs. Although many attack methods can achieve high success rates in the white-box setting, they also exhibit weak…
Due to the limitation of available labeled data, medical image segmentation is a challenging task for deep learning. Traditional data augmentation techniques have been shown to improve segmentation network performances by optimizing the…
Transferring artistic styles onto everyday photographs has become an extremely popular task in both academia and industry. Recently, offline training has replaced on-line iterative optimization, enabling nearly real-time stylization. When…
There is an emerging sense that the vulnerability of Image Convolutional Neural Networks (CNN), i.e., sensitivity to image corruptions, perturbations, and adversarial attacks, is connected with Texture Bias. This relative lack of Shape Bias…
These days deep learning is the fastest-growing area in the field of Machine Learning. Convolutional Neural Networks are currently the main tool used for image analysis and classification purposes. Although great achievements and…
Image style transfer is a challenging task in computational vision. Existing algorithms transfer the color and texture of style images by controlling the neural network's feature layers. However, they fail to control the strength of…