Related papers: Hierarchical Variational Auto-Encoding for Unsuper…
We propose a method to facilitate exploration and analysis of new large data sets. In particular, we give an unsupervised deep learning approach to learning a latent representation that captures semantic similarity in the data set. The core…
Unsupervised feature selection is an important method to reduce dimensions of high dimensional data without labels, which is benefit to avoid ``curse of dimensionality'' and improve the performance of subsequent machine learning tasks, like…
We introduce Domain-specific Masks for Generalization, a model for improving both in-domain and out-of-domain generalization performance. For domain generalization, the goal is to learn from a set of source domains to produce a single model…
Generating versatile and appropriate synthetic speech requires control over the output expression separate from the spoken text. Important non-textual speech variation is seldom annotated, in which case output control must be learned in an…
Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Previous methods focus on learning domain-invariant features to decrease the discrepancy between the feature distributions…
The ability to categorize is a cornerstone of visual intelligence, and a key functionality for artificial, autonomous visual machines. This problem will never be solved without algorithms able to adapt and generalize across visual domains.…
Unsupervised meta-learning aims to learn feature representations from unsupervised datasets that can transfer to downstream tasks with limited labeled data. In this paper, we propose a novel approach to unsupervised meta-learning that…
Unsupervised domain adaptation aims at transferring knowledge from the labeled source domain to the unlabeled target domain. Previous adversarial domain adaptation methods mostly adopt the discriminator with binary or $K$-dimensional output…
The goal of domain generalization is to learn from multiple source domains to generalize to unseen target domains under distribution discrepancy. Current state-of-the-art methods in this area are fully supervised, but for many real-world…
Understanding how deep convolutional neural networks classify data has been subject to extensive research. This paper proposes a technique to visualize and interpret intermediate layers of unsupervised deep convolutional networks by…
We introduce a framework for unsupervised learning of structured predictors with overlapping, global features. Each input's latent representation is predicted conditional on the observable data using a feature-rich conditional random field.…
Recent years have witnessed tremendous interest in deep learning on graph-structured data. Due to the high cost of collecting labeled graph-structured data, domain adaptation is important to supervised graph learning tasks with limited…
We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsupervised tasks, but also…
Probabilistic models with hierarchical-latent-variable structures provide state-of-the-art results amongst non-autoregressive, unsupervised density-based models. However, the most common approach to training such models based on Variational…
Current supervised learning models cannot generalize well across domain boundaries, which is a known problem in many applications, such as robotics or visual classification. Domain adaptation methods are used to improve these generalization…
Thanks to the recent development of deep generative models, it is becoming possible to generate high-quality images with both fidelity and diversity. However, the training of such generative models requires a large dataset. To reduce the…
Deep learning models can achieve high accuracy when trained on large amounts of labeled data. However, real-world scenarios often involve several challenges: Training data may become available in installments, may originate from multiple…
Domain generalization approaches aim to learn a domain invariant prediction model for unknown target domains from multiple training source domains with different distributions. Significant efforts have recently been committed to broad…
Accurate lane detection, a crucial enabler for autonomous driving, currently relies on obtaining a large and diverse labeled training dataset. In this work, we explore learning from abundant, randomly generated synthetic data, together with…
Deep neural networks can model images with rich latent representations, but they cannot naturally conceptualize structures of object categories in a human-perceptible way. This paper addresses the problem of learning object structures in an…