Related papers: Balanced Direction from Multifarious Choices: Arit…
Meta-learning provides a promising way for learning to efficiently learn and achieves great success in many applications. However, most meta-learning literature focuses on dealing with tasks from a same domain, making it brittle to…
Machine learning models are intrinsically vulnerable to domain shift between training and testing data, resulting in poor performance in novel domains. Domain generalization (DG) aims to overcome the problem by leveraging multiple source…
Domain generalization (DG) is about learning models that generalize well to new domains that are related to, but different from, the training domain(s). It is a fundamental problem in machine learning and has attracted much attention in…
Traditional place categorization approaches in robot vision assume that training and test images have similar visual appearance. Therefore, any seasonal, illumination and environmental changes typically lead to severe degradation in…
We propose associative domain adaptation, a novel technique for end-to-end domain adaptation with neural networks, the task of inferring class labels for an unlabeled target domain based on the statistical properties of a labeled source…
We present CROSSGRAD, a method to use multi-domain training data to learn a classifier that generalizes to new domains. CROSSGRAD does not need an adaptation phase via labeled or unlabeled data, or domain features in the new domain. Most…
Many real-world data are sequentially collected over time and often exhibit skewed class distributions, resulting in imbalanced data streams. While existing approaches have explored several strategies, such as resampling and reweighting,…
Computer vision has flourished in recent years thanks to Deep Learning advancements, fast and scalable hardware solutions and large availability of structured image data. Convolutional Neural Networks trained on supervised tasks with…
A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. However, this assumption is violated in almost all practical applications: machine learning…
We propose a novel approach for domain generalisation (DG) leveraging risk distributions to characterise domains, thereby achieving domain invariance. In our findings, risk distributions effectively highlight differences between training…
Unsupervised Domain Adaptation (UDA) aims to generalize the knowledge learned from a well-labeled source domain to an unlabeled target domain. Recently, adversarial domain adaptation with two distinct classifiers (bi-classifier) has been…
The computer vision community is witnessing an unprecedented rate of new tasks being proposed and addressed, thanks to the deep convolutional networks' capability to find complex mappings from X to Y. The advent of each task often…
A dominant approach for addressing unsupervised domain adaptation is to map data points for the source and the target domains into an embedding space which is modeled as the output-space of a shared deep encoder. The encoder is trained to…
The importance of building semantic parsers which can be applied to new domains and generate programs unseen at training has long been acknowledged, and datasets testing out-of-domain performance are becoming increasingly available.…
Unsupervised Domain Adaptation (UDA) approaches address the covariate shift problem by minimizing the distribution discrepancy between the source and target domains, assuming that the label distribution is invariant across domains. However,…
Domain adaptation (DA) is the topical problem of adapting models from labelled source datasets so that they perform well on target datasets where only unlabelled or partially labelled data is available. Many methods have been proposed to…
Federated Domain Generalization aims to learn a domain-invariant model from multiple decentralized source domains for deployment on unseen target domain. Due to privacy concerns, the data from different source domains are kept isolated,…
Machine learning systems must adapt to data distributions that evolve over time, in applications ranging from sensor networks and self-driving car perception modules to brain-machine interfaces. We consider gradual domain adaptation, where…
Domain-invariant representation learning is a powerful method for domain generalization. Previous approaches face challenges such as high computational demands, training instability, and limited effectiveness with high-dimensional data,…
Supervised learning results typically rely on assumptions of i.i.d. data. Unfortunately, those assumptions are commonly violated in practice. In this work, we tackle such problem by focusing on domain generalization: a formalization where…