Related papers: Sample and Predict Your Latent: Modality-free Sequ…

We aim to separate the generative factors of data into two latent vectors in a variational autoencoder. One vector captures class factors relevant to target classification tasks, while the other vector captures style factors relevant to the…

Convolutional networks have marked their place over the last few years as the best performing model for various visual tasks. They are, however, most suited for supervised learning from large amounts of labeled data. Previous attempts have…

Self-supervision is one of the hallmarks of representation learning in the increasingly popular suite of foundation models including large language models such as BERT and GPT-3, but it has not been pursued in the context of multivariate…

Disentangled Representation Learning aims to improve the explainability of deep learning methods by training a data encoder that identifies semantically meaningful latent variables in the data generation process. Nevertheless, there is no…

Recent advances in supervised deep learning methods are enabling remote measurements of photoplethysmography-based physiological signals using facial videos. The performance of these supervised methods, however, are dependent on the…

There is a vast literature on representation learning based on principles such as coding efficiency, statistical independence, causality, controllability, or symmetry. In this paper we propose to learn representations from sequence data by…

We contribute an unsupervised method that effectively learns disentangled content and style representations from sequences of observations. Unlike most disentanglement algorithms that rely on domain-specific labels or knowledge, our method…

In unsupervised learning, dimensionality reduction is an important tool for data exploration and visualization. Because these aims are typically open-ended, it can be useful to frame the problem as looking for patterns that are enriched in…

Learning a discriminative semantic space using unlabelled and noisy data remains unaddressed in a multi-label setting. We present a contrastive self-supervised learning method which is robust to data noise, grounded in the domain of…

Disentangled and invariant representations are two critical goals of representation learning and many approaches have been proposed to achieve either one of them. However, those two goals are actually complementary to each other so that we…

Our work focuses on unsupervised and generative methods that address the following goals: (a) learning unsupervised generative representations that discover latent factors controlling image semantic attributes, (b) studying how this ability…

We investigate a strategy for improving the efficiency of contrastive learning of visual representations by leveraging a small amount of supervised information during pre-training. We propose a semi-supervised loss, SuNCEt, based on…

Learning interpretable and disentangled representations is a crucial yet challenging task in representation learning. In this work, we focus on semi-supervised disentanglement learning and extend work by Locatello et al. (2019) by…

Contrastive learning methods have attracted considerable attention due to their remarkable success in analyzing graph-structured data. Inspired by the success of contrastive learning, we propose a novel framework for contrastive…

(Very early draft)Traditional supervised learning keeps pushing convolution neural network(CNN) achieving state-of-art performance. However, lack of large-scale annotation data is always a big problem due to the high cost of it, even…

We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner. Inspired by recent contrastive self-supervised learning algorithms used for image and NLP pretraining,…

For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker…

Learning disentangled representations is considered a cornerstone problem in representation learning. Recently, Locatello et al. (2019) demonstrated that unsupervised disentanglement learning without inductive biases is theoretically…

In unsupervised causal representation learning for sequential data with time-delayed latent causal influences, strong identifiability results for the disentanglement of causally-related latent variables have been established in stationary…

Unsupervised sentence representation learning is one of the fundamental problems in natural language processing with various downstream applications. Recently, contrastive learning has been widely adopted which derives high-quality sentence…