Skip to search formSkip to main contentSkip to account menu

Unsupervised Domain Adaptation by Domain Invariant Projection

This paper learns a projection of the data to a low-dimensional latent space where the distance between the empirical distributions of the source and target examples is minimized and demonstrates the effectiveness of the approach on the task of visual object recognition.
View on IEEE (opens in a new tab)

Learning to Diversify for Single Domain Generalization

This paper proposes a style-complement module to enhance the generalization power of the model by synthesizing images from diverse distributions that are complementary to the source ones, and surpasses the state-of-the-art single-DG methods by up to 25.14%.
View on IEEE (opens in a new tab)

Progressive Graph Learning for Open-Set Domain Adaptation

This paper introduces an end-to-end Progressive Graph Learning (PGL) framework where a graph neural network with episodic training is integrated to suppress underlying conditional shift and adversarial learning is adopted to close the gap between the source and target distributions.
View PDF on arXiv (opens in a new tab)

Distribution-Matching Embedding for Visual Domain Adaptation

This paper introduces a Distribution-Matching Embedding approach: An unsupervised domain adaptation method that overcomes this issue by mapping the data to a latent space where the distance between the empirical distributions of the source and target examples is minimized.
View Paper (opens in a new tab)

Domain Adaptation on the Statistical Manifold

This framework introduces a sample selection method and a subspace-based method for unsupervised domain adaptation, and shows that both these manifold-based techniques outperform the corresponding approaches based on the MMD.
View on IEEE (opens in a new tab)

Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs

This work proposes to go beyond state-of-the-art image-set matching techniques and model image-sets as probability distribution functions (PDFs) using kernel density estimators and introduces valid positive definite kernels on the statistical manifolds.
View on IEEE (opens in a new tab)

On Minimum Discrepancy Estimation for Deep Domain Adaptation

A new unsupervised deep domain adaptation method based on the alignment of second order statistics (covariances) as well as maximum mean discrepancy of the source and target data with a two stream Convolutional Neural Network (CNN).
View PDF on arXiv (opens in a new tab)

Implicit Surface Representations As Layers in Neural Networks

This work proposes a novel formulation that permits the use of implicit representations of curves and surfaces, of arbitrary topology, as individual layers in Neural Network architectures with end-to-end trainability, and proposes to represent the output as an oriented level set of a continuous and discretised embedding function.
View on IEEE (opens in a new tab)

R1SVM: A Randomised Nonlinear Approach to Large-Scale Anomaly Detection

This paper proposes the RandomisedOne-class SVM (R1SVM), which is an efficient and scalable anomaly detection technique that can be trained on large-scale datasets and achieves comparable or better accuracy to deep autoen-coder and traditional kernelised approaches for anomaly de-tection.
View via Publisher (opens in a new tab)

Robust Domain Generalisation by Enforcing Distribution Invariance

This work proposes Elliptical Summary Randomisation (ESRand), an efficient domain generalisation approach that comprises of a randomised kernel and elliptical data summarisation that learns a domain interdependent projection to a latent subspace that minimises the existing biases to the data while maintaining the functional relationship between domains.
View Paper (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)