Related papers: Syntax and Domain Aware Model for Unsupervised Pro…

Semantic segmentation models based on convolutional neural networks have recently displayed remarkable performance for a multitude of applications. However, these models typically do not generalize well when applied on new domains,…

State-of-the-art neural machine translation (NMT) systems are data-hungry and perform poorly on new domains with no supervised data. As data collection is expensive and infeasible in many cases, domain adaptation methods are needed. In this…

Unsupervised Domain Adaptation (UDA) aims to classify unlabeled target domain by transferring knowledge from labeled source domain with domain shift. Most of the existing UDA methods try to mitigate the adverse impact induced by the shift…

Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding spaces. Successfully solving this problem…

Multi-Source Domain Adaptation (MSDA) deals with the transfer of task knowledge from multiple labeled source domains to an unlabeled target domain, under a domain-shift. Existing methods aim to minimize this domain-shift using auxiliary…

Recent works have proven that many relevant visual tasks are closely related one to another. Yet, this connection is seldom deployed in practice due to the lack of practical methodologies to transfer learned concepts across different…

Cross-lingual representation learning transfers knowledge from resource-rich data to resource-scarce ones to improve the semantic understanding abilities of different languages. However, previous works rely on shallow unsupervised data…

Unsupervised Domain Adaptation (UDA) is essential for enabling semantic segmentation in new domains without requiring costly pixel-wise annotations. State-of-the-art (SOTA) UDA methods primarily use self-training with architecturally…

Achieving satisfying performance in machine translation on domains for which there is no training data is challenging. Traditional supervised domain adaptation is not suitable for addressing such zero-resource domains because it relies on…

The availability of parallel sentence simplification (SS) is scarce for neural SS modelings. We propose an unsupervised method to build SS corpora from large-scale bilingual translation corpora, alleviating the need for SS supervised…

Deep learning models have achieved great success on various vision challenges, but a well-trained model would face drastic performance degradation when applied to unseen data. Since the model is sensitive to domain shift, unsupervised…

This work presents methods for learning cross-lingual sentence representations using paired or unpaired bilingual texts. We hypothesize that the cross-lingual alignment strategy is transferable, and therefore a model trained to align only…

In the context of neural machine translation, data augmentation (DA) techniques may be used for generating additional training samples when the available parallel data are scarce. Many DA approaches aim at expanding the support of the…

Most modern unsupervised domain adaptation (UDA) approaches are rooted in domain alignment, i.e., learning to align source and target features to learn a target domain classifier using source labels. In semi-supervised domain adaptation…

Given a single image x from domain A and a set of images from domain B, our task is to generate the analogous of x in B. We argue that this task could be a key AI capability that underlines the ability of cognitive agents to act in the…

Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool.…

Unsupervised domain adaptation (UDA) adapts a model trained on one domain (called source) to a novel domain (called target) using only unlabeled data. Due to its high annotation cost, researchers have developed many UDA methods for semantic…

Image-to-image translation architectures may have limited effectiveness in some circumstances. For example, while generating rainy scenarios, they may fail to model typical traits of rain as water drops, and this ultimately impacts the…

Unsupervised video domain adaptation (UVDA) is a practical but under-explored problem. In this paper, we propose a frustratingly easy UVDA method, called MetaTrans. Specifically, MetaTrans adopts a concise learning objective that contains…

Preservation of domain knowledge from the source to target is crucial in any translation workflow. It is common in the translation industry to receive highly specialized projects, where there is hardly any parallel in-domain data. In such…