Related papers: On the Transferability of VAE Embeddings using Rel…

While Semi-supervised learning has gained much attention in computer vision on image data, yet limited research exists on its applicability in the time series domain. In this work, we investigate the transferability of state-of-the-art deep…

Text style transfer task requires the model to transfer a sentence of one style to another style while retaining its original content meaning, which is a challenging problem that has long suffered from the shortage of parallel data. In this…

Recent work shows that documents from encyclopedias serve as helpful auxiliary information for zero-shot learning. Existing methods align the entire semantics of a document with corresponding images to transfer knowledge. However, they…

Semi-supervised learning is becoming increasingly important because it can combine data carefully labeled by humans with abundant unlabeled data to train deep neural networks. Classic methods on semi-supervised learning that have focused on…

To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like…

Learning representations with self-supervision for convolutional networks (CNN) has been validated to be effective for vision tasks. As an alternative to CNN, vision transformers (ViT) have strong representation ability with spatial…

Vision Transformer (ViT) suffers from data scarcity in semi-supervised learning (SSL). To alleviate this issue, inspired by masked autoencoder (MAE), which is a data-efficient self-supervised learner, we propose Semi-MAE, a pure ViT-based…

Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of…

We present a new approach to disentangle speaker voice and phone content by introducing new components to the VQ-VAE architecture for speech synthesis. The original VQ-VAE does not generalize well to unseen speakers or content. To alleviate…

As an important and challenging problem in computer vision, zero-shot learning (ZSL) aims at automatically recognizing the instances from unseen object classes without training data. To address this problem, ZSL is usually carried out in…

We study the problem of learning representations of entities and relations in knowledge graphs for predicting missing links. The success of such a task heavily relies on the ability of modeling and inferring the patterns of (or between) the…

Improving controllability or the ability to manipulate one or more attributes of the generated data has become a topic of interest in the context of deep generative models of music. Recent attempts in this direction have relied on learning…

Although semi-supervised variational autoencoder (SemiVAE) works in image classification task, it fails in text classification task if using vanilla LSTM as its decoder. From a perspective of reinforcement learning, it is verified that the…

Knowledge representation is a major topic in AI, and many studies attempt to represent entities and relations of knowledge base in a continuous vector space. Among these attempts, translation-based methods build entity and relation vectors…

Zero-shot Learning (ZSL) is a transfer learning technique which aims at transferring knowledge from seen classes to unseen classes. This knowledge transfer is possible because of underlying semantic space which is common to seen and unseen…

Supervised representation learning with deep networks tends to overfit the training classes and the generalization to novel classes is a challenging question. It is common to evaluate a learned embedding on held-out images of the same…

Current Visual Question Answering (VQA) systems can answer intelligent questions about `Known' visual content. However, their performance drops significantly when questions about visually and linguistically `Unknown' concepts are presented…

Representation learning has overcome the often arduous and manual featurization of networks through (unsupervised) feature learning as it results in embeddings that can apply to a variety of downstream learning tasks. The focus of…

We propose to learn model invariances as a means of interpreting a model. This is motivated by a reverse engineering principle. If we understand a problem, we may introduce inductive biases in our model in the form of invariances.…

While different neural models often exhibit latent spaces that are alike when exposed to semantically related data, this intrinsic similarity is not always immediately discernible. Towards a better understanding of this phenomenon, our work…