Related papers: Adversarial Style Augmentation for Domain Generali…
In real-world applications, the sample distribution at the inference stage often differs from the one at the training stage, causing performance degradation of trained deep models. The research on domain generalization (DG) aims to develop…
Training a semantic segmentation model requires a large amount of pixel-level annotation, hampering its application at scale. With computer graphics, we can generate almost unlimited training data with precise annotation. However,a deep…
Unsupervised domain adaption aims to learn a powerful classifier for the target domain given a labeled source data set and an unlabeled target data set. To alleviate the effect of `domain shift', the major challenge in domain adaptation,…
Performance achievable by modern deep learning approaches are directly related to the amount of data used at training time. Unfortunately, the annotation process is notoriously tedious and expensive, especially for pixel-wise tasks like…
Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks. One appealing alternative is rendering synthetic data where ground-truth annotations are generated…
Most statistical learning algorithms rely on an over-simplified assumption, that is, the train and test data are independent and identically distributed. In real-world scenarios, however, it is common for models to encounter data from new…
Domain generalization aims to enhance the model robustness against domain shift without accessing the target domain. Since the available source domains for training are limited, recent approaches focus on generating samples of novel…
Domain adaptation is widely used in learning problems lacking labels. Recent studies show that deep adversarial domain adaptation models can make markable improvements in performance, which include symmetric and asymmetric architectures.…
Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data…
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…
Histopathological images are essential for medical diagnosis and treatment planning, but interpreting them accurately using machine learning can be challenging due to variations in tissue preparation, staining and imaging protocols. Domain…
Despite great progress in supervised semantic segmentation,a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain.…
We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from…
Though convolutional neural networks (CNNs) have demonstrated remarkable ability in learning discriminative features, they often generalize poorly to unseen domains. Domain generalization aims to address this problem by learning from a set…
To be successful in single source domain generalization, maximizing diversity of synthesized domains has emerged as one of the most effective strategies. Many of the recent successes have come from methods that pre-specify the types of…
Generative adversarial networks (GANs) have made remarkable achievements in synthesizing images in recent years. Typically, training GANs requires massive data, and the performance of GANs deteriorates significantly when training data is…
Data augmentation is a major component of many machine learning methods with state-of-the-art performance. Common augmentation strategies work by drawing random samples from a space of transformations. Unfortunately, such sampling…
Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available…
While deep face recognition models have demonstrated remarkable performance, they often struggle on the inputs from domains beyond their training data. Recent attempts aim to expand the training set by relying on computationally expensive…
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…