Related papers: Augmentation-Interpolative AutoEncoders for Unsupe…

We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. Here, regularized autoencoders provide a popular approach by learning the identity mapping on the…

Modern neural networks are over-parameterized and thus rely on strong regularization such as data augmentation and weight decay to reduce overfitting and improve generalization. The dominant form of data augmentation applies invariant…

Learning disentangled representations from visual data, where different high-level generative factors are independently encoded, is of importance for many computer vision tasks. Solving this problem, however, typically requires to…

Text-to-image generation requires large amount of training data to synthesizing high-quality images. For augmenting training data, previous methods rely on data interpolations like cropping, flipping, and mixing up, which fail to introduce…

We present a general-purpose framework for image modelling and vision tasks based on probabilistic frame prediction. Our approach unifies a broad range of tasks, from image segmentation, to novel view synthesis and video interpolation. We…

With the availability of powerful text-to-image diffusion models, recent works have explored the use of synthetic data to improve image classification performances. These works show that it can effectively augment or even replace real data.…

Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks. One appealing alternative is rendering synthetic data where ground-truth annotations are generated…

State-of-the-art techniques in Generative Adversarial Networks (GANs) have shown remarkable success in image-to-image translation from peer domain X to domain Y using paired image data. However, obtaining abundant paired data is a…

This paper investigates the problem of image classification with limited or no annotations, but abundant unlabeled data. The setting exists in many tasks such as semi-supervised image classification, image clustering, and image retrieval.…

Current developments in computer vision and deep learning allow to automatically generate hyper-realistic images, hardly distinguishable from real ones. In particular, human face generation achieved a stunning level of realism, opening new…

Although high resolution isotropic 3D medical images are desired in clinical practice, their acquisition is not always feasible. Instead, lower resolution images are upsampled to higher resolution using conventional interpolation methods.…

Extrapolating fine-grained pixel-level correspondences in a fully unsupervised manner from a large set of misaligned images can benefit several computer vision and graphics problems, e.g. co-segmentation, super-resolution, image edit…

Enhanced modeling of microlensing variations in light curves of strongly lensed quasars improves measurements of cosmological time delays, the Hubble Constant, and quasar structure. Traditional methods for modeling extra-galactic…

We investigate using reinforcement learning agents as generative models of images (extending arXiv:1804.01118). A generative agent controls a simulated painting environment, and is trained with rewards provided by a discriminator network…

Increasing the resolution of image sensors has been a never ending struggle since many years. In this paper, we propose a novel image sensor layout which allows for the acquisition of images at a higher resolution and improved quality. For…

Few-shot image generation and few-shot image translation are two related tasks, both of which aim to generate new images for an unseen category with only a few images. In this work, we make the first attempt to adapt few-shot image…

Improving the aesthetic quality of images is challenging and eager for the public. To address this problem, most existing algorithms are based on supervised learning methods to learn an automatic photo enhancer for paired data, which…

We propose a novel approach to synthesizing images that are effective for training object detectors. Starting from a small set of real images, our algorithm estimates the rendering parameters required to synthesize similar images given a…

Attribute guided face image synthesis aims to manipulate attributes on a face image. Most existing methods for image-to-image translation can either perform a fixed translation between any two image domains using a single attribute or…

In this paper, we study the importance of pre-training for the generalization capability in the color constancy problem. We propose two novel approaches based on convolutional autoencoders: an unsupervised pre-training algorithm using a…