相关论文: Langevin Cooling for Domain Translation

Multi-modal domain translation typically refers to synthesizing a novel image that inherits certain localized attributes from a 'content' image (e.g. layout, semantics, or geometry), and inherits everything else (e.g. texture, lighting,…

Domain adaptation investigates the problem of cross-domain knowledge transfer where the labeled source domain and unlabeled target domain have distinctive data distributions. Recently, adversarial training have been successfully applied to…

We explore best practices for training small, memory efficient machine translation models with sequence-level knowledge distillation in the domain adaptation setting. While both domain adaptation and knowledge distillation are widely-used,…

This early-stage research work aims to improve online human-robot imitation by translating sequences of joint positions from the domain of human motions to a domain of motions achievable by a given robot, thus constrained by its embodiment.…

Thanks to large-scale labeled training data, deep neural networks (DNNs) have obtained remarkable success in many vision and multimedia tasks. However, because of the presence of domain shift, the learned knowledge of the well-trained DNNs…

Standard domain adaptation methods do not work well when a large gap exists between the source and target domains. Gradual domain adaptation is one of the approaches used to address the problem. It involves leveraging the intermediate…

Deep neural networks are able to learn powerful representations from large quantities of labeled input data, however they cannot always generalize well across changes in input distributions. Domain adaptation algorithms have been proposed…

Foundation models have achieved great success in natural language processing (NLP) and computer vision (CV). Their success largely stems from the ability to integrate multi-domain knowledge in pre-training and transfer it to target domains.…

We propose a general framework for unsupervised domain adaptation, which allows deep neural networks trained on a source domain to be tested on a different target domain without requiring any training annotations in the target domain. This…

Stochastic Langevin dynamics has been traditionally used as a tool to describe non-equilibrium processes. When utilized in systems with collective modes, traditional Langevin dynamics relaxes all modes indiscriminately, regardless of their…

Unpaired image-to-image translation (UNIT) aims to map images between two visual domains without paired training data. However, given a UNIT model trained on certain domains, it is difficult for current methods to incorporate new domains…

Thanks to digitization of industrial assets in fleets, the ambitious goal of transferring fault diagnosis models fromone machine to the other has raised great interest. Solving these domain adaptive transfer learning tasks has the potential…

This paper presents Fd-CycleGAN, an image-to-image (I2I) translation framework that enhances latent representation learning to approximate real data distributions. Building upon the foundation of CycleGAN, our approach integrates Local…

We cast the problem of image denoising as a domain translation problem between high and low noise domains. By modifying the cycleGAN model, we are able to learn a mapping between these domains on unpaired retinal optical coherence…

Model-free deep reinforcement learning (RL) agents can learn an effective policy directly from repeated interactions with a black-box environment. However in practice, the algorithms often require large amounts of training experience to…

It has been previously noted that neural machine translation (NMT) is very sensitive to domain shift. In this paper, we argue that this is a dual effect of the highly lexicalized nature of NMT, resulting in failure for sentences with large…

Recent works of multi-source domain adaptation focus on learning a domain-agnostic model, of which the parameters are static. However, such a static model is difficult to handle conflicts across multiple domains, and suffers from a…

Although a machine translation model trained with a large in-domain parallel corpus achieves remarkable results, it still works poorly when no in-domain data are available. This situation restricts the applicability of machine translation…

Many multi-domain neural machine translation (NMT) models achieve knowledge transfer by enforcing one encoder to learn shared embedding across domains. However, this design lacks adaptation to individual domains. To overcome this…

Semantic communication can significantly improve bandwidth utilization in wireless systems by exploiting the meaning behind raw data. However, the advancements achieved through semantic communication are closely dependent on the development…