相关论文: Domain-adaptation of spherical embeddings

Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) deal with all the samples from the two domains in a global or category-aware manner. They do…

We propose a method for unsupervised domain adaptation that trains a shared embedding to align the joint distributions of inputs (domain) and outputs (classes), making any classifier agnostic to the domain. Joint alignment ensures that not…

Despite domain generalization (DG) has significantly addressed the performance degradation of pre-trained models caused by domain shifts, it often falls short in real-world deployment. Test-time adaptation (TTA), which adjusts a learned…

Cross-modal image translation remains brittle and inefficient. Standard diffusion approaches often rely on a single, global linear transfer between domains. We find that this shortcut forces the sampler to traverse off-manifold, high-cost…

Transfer learning methods, and in particular domain adaptation, help exploit labeled data in one domain to improve the performance of a certain task in another domain. However, it is still not clear what factors affect the success of domain…

We develop an algorithm for adapting a semantic segmentation model that is trained using a labeled source domain to generalize well in an unlabeled target domain. A similar problem has been studied extensively in the unsupervised domain…

Recently, Le and Mikolov (2014) proposed doc2vec as an extension to word2vec (Mikolov et al., 2013a) to learn document-level embeddings. Despite promising results in the original paper, others have struggled to reproduce those results. This…

A currently successful approach to computational semantics is to represent words as embeddings in a machine-learned vector space. We present an ensemble method that combines embeddings produced by GloVe (Pennington et al., 2014) and…

Regularization of neural machine translation is still a significant problem, especially in low-resource settings. To mollify this problem, we propose regressing word embeddings (ReWE) as a new regularization technique in a system that is…

Learning effective sentence representations is crucial for many Natural Language Processing (NLP) tasks, including semantic search, semantic textual similarity (STS), and clustering. While multiple transformer models have been developed for…

Domain Adaptation is the process of alleviating distribution gaps between data from different domains. In this paper, we show that Domain Adaptation methods using pair-wise relationships between source and target domain data can be…

Word2vec is one of the most used algorithms to generate word embeddings because of a good mix of efficiency, quality of the generated representations and cognitive grounding. However, word meaning is not static and depends on the context in…

Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making…

Comparing spoken segments is a central operation to speech processing. Traditional approaches in this area have favored frame-level dynamic programming algorithms, such as dynamic time warping, because they require no supervision, but they…

Domain-adaptive pre-training (or DA-training for short), also known as post-training, aims to train a pre-trained general-purpose language model (LM) using an unlabeled corpus of a particular domain to adapt the LM so that end-tasks in the…

This work investigates the role of factors like training method, training corpus size and thematic relevance of texts in the performance of word embedding features on sentiment analysis of tweets, song lyrics, movie reviews and item…

Foundation models (FMs) have revolutionized computer vision, enabling effective learning across different domains. However, their performance under domain shift is yet underexplored. This paper investigates the zero-shot domain adaptation…

Traditional information retrieval (such as that offered by web search engines) impedes users with information overload from extensive result pages and the need to manually locate the desired information therein. Conversely,…

Word embeddings are representations of individual words of a text document in a vector space and they are often use- ful for performing natural language pro- cessing tasks. Current state of the art al- gorithms for learning word embeddings…

In forecasting multiple time series, accounting for the individual features of each sequence can be challenging. To address this, modern deep learning methods for time series analysis combine a shared (global) model with local layers,…