Related papers: Deep Subdomain Adaptation Network for Image Classi…
Getting deep convolutional neural networks to perform well requires a large amount of training data. When the available labelled data is small, it is often beneficial to use transfer learning to leverage a related larger dataset (source) in…
Despite their success in many computer vision tasks, convolutional networks tend to require large amounts of labeled data to achieve generalization. Furthermore, the performance is not guaranteed on a sample from an unseen domain at test…
Unsupervised domain adaptation seeks to mitigate the distribution discrepancy between source and target domains, given labeled samples of the source domain and unlabeled samples of the target domain. Generative adversarial networks (GANs)…
Supervised learning with large scale labeled datasets and deep layered models has made a paradigm shift in diverse areas in learning and recognition. However, this approach still suffers generalization issues under the presence of a domain…
Domain adaptation aims to leverage a label-rich domain (the source domain) to help model learning in a label-scarce domain (the target domain). Most domain adaptation methods require the co-existence of source and target domain samples to…
Change detection (CD) is one of the most vital applications in remote sensing. Recently, deep learning has achieved promising performance in the CD task. However, the deep models are task-specific and CD data set bias often exists, hence it…
Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain adaptation (DA). Conventional DA methods usually assume that…
Significant inter-individual variability limits the generalization of EEG-based emotion recognition under cross-domain settings. We address two core challenges in multi-source adaptation: (1) dynamically modeling distributional…
Conventional cross-domain image-to-image translation or unsupervised domain adaptation methods assume that the source domain and target domain are closely related. This neglects a practical scenario where the domain discrepancy between the…
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…
Unsupervised domain adaptation for object detection addresses the adaption of detectors trained in a source domain to work accurately in an unseen target domain. Recently, methods approaching the alignment of the intermediate features…
Domain adaptation aims to bridge the domain shifts between the source and the target domain. These shifts may span different dimensions such as fog, rainfall, etc. However, recent methods typically do not consider explicit prior knowledge…
Transfer learning has emerged as a powerful methodology for adapting pre-trained deep neural networks on image recognition tasks to new domains. This process consists of taking a neural network pre-trained on a large feature-rich source…
Domain generalization approaches aim to learn a domain invariant prediction model for unknown target domains from multiple training source domains with different distributions. Significant efforts have recently been committed to broad…
Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not…
In many practical visual recognition scenarios, feature distribution in the source domain is generally different from that of the target domain, which results in the emergence of general cross-domain visual recognition problems. To address…
Deep learning-based object reconstruction algorithms have shown remarkable improvements over classical methods. However, supervised learning based methods perform poorly when the training data and the test data have different distributions.…
We present a new semi-supervised domain adaptation framework that combines a novel auto-encoder-based domain adaptation model with a simultaneous learning scheme providing stable improvements over state-of-the-art domain adaptation models.…
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…
This paper presents a novel multi-task learning-based method for unsupervised domain adaptation. Specifically, the source and target domain classifiers are jointly learned by considering the geometry of target domain and the divergence…