Related papers: Set Distribution Networks: a Generative Model for …

In applications involving matching of image sets, the information from multiple images must be effectively exploited to represent each set. State-of-the-art methods use probabilistic distribution or subspace to model a set and use specific…

Steganography usually modifies cover media to embed secret data. A new steganographic approach called generative steganography (GS) has emerged recently, in which stego images (images containing secret data) are generated from secret data…

In forensic investigations of machine learning models, techniques that determine a model's data domain play an essential role, with prior work relying on large-scale corpora like ImageNet to approximate the target model's domain. Although…

Many imaging tasks require global information about all pixels in an image. Conventional bottom-up classification networks globalize information by decreasing resolution; features are pooled and downsampled into a single output. But for…

Despite recent advancements in single-domain or single-object image generation, it is still challenging to generate complex scenes containing diverse, multiple objects and their interactions. Scene graphs, composed of nodes as objects and…

Most current computer vision datasets are composed of disconnected sets, such as images from different classes. We prove that distributions of this type of data cannot be represented with a continuous generative network without error. They…

Generative models are nowadays widely used to generate graphical content used for multiple purposes, e.g. web, art, advertisement. However, it has been shown that the images generated by these models could reinforce societal biases already…

Person Re-identification (re-id) faces two major challenges: the lack of cross-view paired training data and learning discriminative identity-sensitive and view-invariant features in the presence of large pose variations. In this work, we…

Convolutional neural networks (CNNs) tend to become a standard approach to solve a wide array of computer vision problems. Besides important theoretical and practical advances in their design, their success is built on the existence of…

Generative models capture the true distribution of data, yielding semantically rich representations. Denoising diffusion models (DDMs) exhibit superior generative capabilities, though efficient representation learning for them are lacking.…

Facial recognition using deep convolutional neural networks relies on the availability of large datasets of face images. Many examples of identities are needed, and for each identity, a large variety of images are needed in order for the…

One of the key challenges of detecting AI-generated images is spotting images that have been created by previously unseen generative models. We argue that the limited diversity of the training data is a major obstacle to addressing this…

Convolutional neural networks (CNNs) are one of the most popular models of Artificial Neural Networks (ANN)s in Computer Vision (CV). A variety of CNN-based structures were developed by researchers to solve problems like image…

Training deep networks with limited labeled data while achieving a strong generalization ability is key in the quest to reduce human annotation efforts. This is the goal of semi-supervised learning, which exploits more widely available…

We propose a novel architecture which is able to automatically anonymize faces in images while retaining the original data distribution. We ensure total anonymization of all faces in an image by generating images exclusively on privacy-safe…

Stochastic configuration networks (SCNs) as a class of randomized learner model have been successfully employed in data analytics due to its universal approximation capability and fast modelling property. The technical essence lies in…

Histopathology image classification is crucial for the accurate identification and diagnosis of various diseases but requires large and diverse datasets. Obtaining such datasets, however, is often costly and time-consuming due to the need…

Deep image denoising networks have achieved impressive success with the help of a considerably large number of synthetic train datasets. However, real-world denoising is a still challenging problem due to the dissimilarity between…

Advances in image generation enable hyper-realistic synthetic faces but also pose risks, thus making synthetic face detection crucial. Previous research focuses on the general differences between generated images and real images, often…

We address the problem of finding realistic geometric corrections to a foreground object such that it appears natural when composited into a background image. To achieve this, we propose a novel Generative Adversarial Network (GAN)…