Related papers: Adversarial Domain Adaptation for Variational Neur…

Simulation-to-real domain adaptation for semantic segmentation has been actively studied for various applications such as autonomous driving. Existing methods mainly focus on a single-source setting, which cannot easily handle a more…

Unsupervised domain adaptation, which involves transferring knowledge from a label-rich source domain to an unlabeled target domain, can be used to substantially reduce annotation costs in the field of object detection. In this study, we…

In real-world visual recognition problems, the assumption that the training data (source domain) and test data (target domain) are sampled from the same distribution is often violated. This is known as the domain adaptation problem. In this…

Due to the difficulty of obtaining ground-truth labels, learning from virtual-world datasets is of great interest for real-world applications like semantic segmentation. From domain adaptation perspective, the key challenge is to learn…

In this work, we propose a method for neural dialogue response generation that allows not only generating semantically reasonable responses according to the dialogue history, but also explicitly controlling the sentiment of the response via…

Visual Domain Adaptation is a problem of immense importance in computer vision. Previous approaches showcase the inability of even deep neural networks to learn informative representations across domain shift. This problem is more severe…

When a natural language generation (NLG) component is implemented in a real-world task-oriented dialogue system, it is necessary to generate not only natural utterances as learned on training data but also utterances adapted to the dialogue…

Natural language generators (NLGs) for task-oriented dialogue typically take a meaning representation (MR) as input. They are trained end-to-end with a corpus of MR/utterance pairs, where the MRs cover a specific set of dialogue acts and…

Domain adversarial training has shown its effective capability for finding domain invariant feature representations and been successfully adopted for various domain adaptation tasks. However, recent advances of large models (e.g., vision…

Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation. Existing adversarial domain adaptation methods may not effectively align different domains of multimodal…

Whereas adversarial training can be useful against specific adversarial perturbations, they have also proven ineffective in generalizing towards attacks deviating from those used for training. However, we observe that this ineffectiveness…

Domain adaptation is one of the most crucial techniques to mitigate the domain shift problem, which exists when transferring knowledge from an abundant labeled sourced domain to a target domain with few or no labels. Partial domain…

Voice conversion has made great progress in the past few years under the studio-quality test scenario in terms of speech quality and speaker similarity. However, in real applications, test speech from source speaker or target speaker can be…

Autonomous navigation has become an increasingly popular machine learning application. Recent advances in deep learning have also resulted in great improvements to autonomous navigation. However, prior outdoor autonomous navigation depends…

We address the problem of detecting duplicate questions in forums, which is an important step towards automating the process of answering new questions. As finding and annotating such potential duplicates manually is very tedious and…

Adversarial learning baselines for domain adaptation (DA) approaches in the context of semantic segmentation are under explored in semi-supervised framework. These baselines involve solely the available labeled target samples in the…

Deep reinforcement learning agents have recently been successful across a variety of discrete and continuous control tasks; however, they can be slow to train and require a large number of interactions with the environment to learn a…

Current state of the art methods in Domain Adaptation follow adversarial approaches, making training a challenge. Existing non-adversarial methods learn mappings between the source and target domains, to achieve reasonable performance.…

In real-world applications, speaker recognition models often face various domain-mismatch challenges, leading to a significant drop in performance. Although numerous domain adaptation techniques have been developed to address this issue,…

Open domain neural dialogue models, despite their successes, are known to produce responses that lack relevance, diversity, and in many cases coherence. These shortcomings stem from the limited ability of common training objectives to…