Related papers: Copycat CNN: Are Random Non-Labeled Data Enough to…

In this paper, we highlight a critical threat posed by emerging neural models: data plagiarism. We demonstrate how modern neural models (e.g., diffusion models) can replicate copyrighted images, even when protected by advanced watermarking…

Convolutional neural networks (CNN) have proven to be state of the art methods for many image classification tasks and their use is rapidly increasing in remote sensing problems. One of their major strengths is that, when enough data is…

In this paper we show how to learn directly from image data (i.e., without resorting to manually-designed features) a general similarity function for comparing image patches, which is a task of fundamental importance for many computer…

Purpose: The aim of this work is to demonstrate that convolutional neural networks (CNN) can be applied to extremely sparse image libraries by subdivision of the original image datasets. Methods: Image datasets from a conventional digital…

A significant number of machine learning models are vulnerable to model extraction attacks, which focus on stealing the models by using specially curated queries against the target model. This task is well accomplished by using part of the…

Detecting the camera model used to shoot a picture enables to solve a wide series of forensic problems, from copyright infringement to ownership attribution. For this reason, the forensic community has developed a set of camera model…

Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers. Specifically, the standard convolution traverses the input images/features using a sliding window scheme to…

Deep neural networks learn fragile "shortcut" features, rendering them difficult to interpret (black box) and vulnerable to adversarial attacks. This paper proposes semantic features as a general architectural solution to this problem. The…

Copies have been proposed as a viable alternative to endow machine learning models with properties and features that adapt them to changing needs. A fundamental step of the copying process is generating an unlabelled set of points to…

CNNs perform remarkably well when the training and test distributions are i.i.d, but unseen image corruptions can cause a surprisingly large drop in performance. In various real scenarios, unexpected distortions, such as random noise,…

Deep learning algorithms offer a powerful means to automatically analyze the content of medical images. However, many biological samples of interest are primarily transparent to visible light and contain features that are difficult to…

Convolutional Neural Networks (CNNs) for visual tasks are believed to learn both the low-level textures and high-level object attributes, throughout the network depth. This paper further investigates the `texture bias' in CNNs. To this end,…

Imaging systems are increasingly used as input to convolutional neural networks (CNN) for object detection; we would like to design cameras that are optimized for this purpose. It is impractical to build different cameras and then acquire…

It is known that humans display "shape bias" when classifying new items, i.e., they prefer to categorize objects based on their shape rather than color. Convolutional Neural Networks (CNNs) are also designed to take into account the spatial…

Over the past decade deep learning has revolutionized the field of computer vision, with convolutional neural network models proving to be very effective for image classification benchmarks. However, a fundamental theoretical questions…

Convolutional Neural Networks (CNNs) are build specifically for computer vision tasks for which it is known that the input data is a hierarchical structure based on locally correlated elements. The question that naturally arises is what…

The convolutional neural network (CNN) learns the same object in different positions in images, which can improve the recognition accuracy of the model. An implication of this is that CNN may know where the object is. The usefulness of the…

The increasing use of generative ML foundation models for image restoration tasks such as super-resolution calls for robust and interpretable uncertainty quantification methods. We address this need by presenting a novel approach based on…

Recent experiments in computer vision demonstrate texture bias as the primary reason for supreme results in models employing Convolutional Neural Networks (CNNs), conflicting with early works claiming that these networks identify objects…

Despite the success of neural networks (NNs), there is still a concern among many over their "black box" nature. Why do they work? Here we present a simple analytic argument that NNs are in fact essentially polynomial regression models.…