Related papers: Processsing Simple Geometric Attributes with Autoe…

Autoencoders are commonly used in representation learning. They consist of an encoder and a decoder, which provide a straightforward way to map n-dimensional data in input space to a lower m-dimensional representation space and back. The…

3D geometry is a very informative cue when interacting with and navigating an environment. This writing proposes a new approach to 3D reconstruction and scene understanding, which implicitly learns 3D geometry from depth maps pairing a deep…

The problem of learning a manifold structure on a dataset is framed in terms of a generative model, to which we use ideas behind autoencoders (namely adversarial/Wasserstein autoencoders) to fit deep neural networks. From a machine learning…

Standard convolutions are prevalent in image processing and deep learning, but their fixed kernels limits adaptability. Several deformation strategies of the reference kernel grid have been proposed. Yet, they lack a unified theoretical…

Generative adversarial networks (GANs) can synthesize high-quality (HQ) images, and GAN inversion is a technique that discovers how to invert given images back to latent space. While existing methods perform on StyleGAN inversion, they have…

We propose a novel approach for instance-level image retrieval. It produces a global and compact fixed-length representation for each image by aggregating many region-wise descriptors. In contrast to previous works employing pre-trained…

Anomaly detection and localization without any manual annotations and prior knowledge is a challenging task under the setting of unsupervised learning. The existing works achieve excellent performance in the anomaly detection, but with…

We propose a new algorithm for training generative adversarial networks that jointly learns latent codes for both identities (e.g. individual humans) and observations (e.g. specific photographs). By fixing the identity portion of the latent…

Learning the distribution of images in order to generate new samples is a challenging task due to the high dimensionality of the data and the highly non-linear relations that are involved. Nevertheless, some promising results have been…

Previous works have shown that convolutional neural networks can achieve good performance in image denoising tasks. However, limited by the local rigid convolutional operation, these methods lead to oversmoothing artifacts. A deeper network…

While significant attention has been recently focused on designing supervised deep semantic segmentation algorithms for vision tasks, there are many domains in which sufficient supervised pixel-level labels are difficult to obtain. In this…

Our work focuses on tackling large-scale fine-grained image retrieval as ranking the images depicting the concept of interests (i.e., the same sub-category labels) highest based on the fine-grained details in the query. It is desirable to…

In the last few years there have been important advancements in generative models with the two dominant approaches being Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). However, standard Autoencoders (AEs) and…

As machine learning is applied to an increasing variety of complex problems, which are defined by high dimensional and complex data sets, the necessity for task oriented feature learning grows in importance. With the advancement of Deep…

Driving in the dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision policy. The learning of such a policy requires a state representation that can encode the entire environment. Mid-level…

Spatial transformations are enablers in a variety of medical image analysis applications that entail aligning images to a common coordinate systems. Population analysis of such transformations is expected to capture the underlying image and…

Deep feature spaces have the capacity to encode complex transformations of their input data. However, understanding the relative feature-space relationship between two transformed encoded images is difficult. For instance, what is the…

Deep Learning methods usually require huge amounts of training data to perform at their full potential, and often require expensive manual labeling. Using synthetic images is therefore very attractive to train object detectors, as the…

Creating CAD digital twins from the physical world is crucial for manufacturing, design, and simulation. However, current methods typically rely on costly 3D scanning with labor-intensive post-processing. To provide a user-friendly design…

While objects from different categories can be reliably decoded from fMRI brain response patterns, it has proved more difficult to distinguish visually similar inputs, such as different instances of the same category. Here, we apply a…