相关论文: Domain Generalization with Small Data

Existing domain adaptation methods assume that domain discrepancies are caused by a few discrete attributes and variations, e.g., art, real, painting, quickdraw, etc. We argue that this is not realistic as it is implausible to define the…

Domain adaptation (DA) addresses the challenge of transferring knowledge from a source domain to a target domain where image data distributions may differ. Existing DA methods often require access to source domain data, adversarial…

Domain adaptation has become a prominent problem setting in machine learning and related fields. This review asks the question: how can a classifier learn from a source domain and generalize to a target domain? We present a categorization…

Domain adaptation (DA) aims to transfer knowledge from a label-rich source domain to a related but label-scarce target domain. The conventional DA strategy is to align the feature distributions of the two domains. Recently, increasing…

Domain adaptive semantic segmentation is the task of generating precise and dense predictions for an unlabeled target domain using a model trained on a labeled source domain. While significant efforts have been devoted to improving…

Deep domain adaptation methods can reduce the distribution discrepancy by learning domain-invariant embedddings. However, these methods only focus on aligning the whole data distributions, without considering the class-level relations among…

Domain generalization (DG) seeks to develop models that generalize well to unseen target domains, addressing the prevalent issue of distribution shifts in real-world applications. One line of research in DG focuses on aligning domain-level…

Incorporating domain knowledge into the modeling process is an effective way to improve learning accuracy. However, as it is provided by humans, domain knowledge can only be specified with some degree of uncertainty. We propose to…

Despite much progress being made in the field of object recognition with the advances of deep learning, there are still several factors negatively affecting the performance of deep learning models. Domain shift is one of these factors and…

Unsupervised domain adaptation uses source data from different distributions to solve the problem of classifying data from unlabeled target domains. However, conventional methods require access to source data, which often raise concerns…

Efficient medical image segmentation aims to provide accurate pixel-wise predictions for medical images with a lightweight implementation framework. However, lightweight frameworks generally fail to achieve superior performance and suffer…

We tackle the domain generalisation (DG) problem by posing it as a domain adaptation (DA) task where we adversarially synthesise the worst-case target domain and adapt a model to that worst-case domain, thereby improving the model's…

This paper investigates domain generalization: How to take knowledge acquired from an arbitrary number of related domains and apply it to previously unseen domains? We propose Domain-Invariant Component Analysis (DICA), a kernel-based…

Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Previous methods focus on learning domain-invariant features to decrease the discrepancy between the feature distributions…

Remote sensing enables a wide range of critical applications such as land cover and land use mapping, crop yield prediction, and environmental monitoring. Advances in satellite technology have expanded remote sensing datasets, yet…

Class imbalance in supervised classification often degrades model performance by biasing predictions toward the majority class, particularly in critical applications such as medical diagnosis and fraud detection. Traditional oversampling…

Unsupervised domain adaptation (UDA) aims to improve the prediction performance in the target domain under distribution shifts from the source domain. The key principle of UDA is to minimize the divergence between the source and the target…

Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space. To avoid the sampling variability, class imbalance, and data-privacy concerns…

Domain generalization aims to develop models that are robust to distribution shifts. Existing methods focus on learning invariance across domains to enhance model robustness, and data augmentation has been widely used to learn invariant…

We propose to harness the potential of simulation for the semantic segmentation of real-world self-driving scenes in a domain generalization fashion. The segmentation network is trained without any data of target domains and tested on the…