Pseudo labels for unsupervised domain adaptation: A review
Y Li, L Guo, Y Ge - Electronics, 2023 - mdpi.com
Conventional machine learning relies on two presumptions:(1) the training and testing
datasets follow the same independent distribution, and (2) an adequate quantity of samples …
datasets follow the same independent distribution, and (2) an adequate quantity of samples …
Semi-supervised domain adaptation with source label adaptation
Abstract Semi-Supervised Domain Adaptation (SSDA) involves learning to classify unseen
target data with a few labeled and lots of unlabeled target data, along with many labeled …
target data with a few labeled and lots of unlabeled target data, along with many labeled …
Jaws: Auditing predictive uncertainty under covariate shift
Abstract We propose\textbf {JAWS}, a series of wrapper methods for distribution-free
uncertainty quantification tasks under covariate shift, centered on the core method\textbf …
uncertainty quantification tasks under covariate shift, centered on the core method\textbf …
Contrasting augmented features for domain adaptation with limited target domain data
Abstract Domain adaptation aims to alleviate distribution gaps between source and target
domains. However, when the available target domain data are scarce for training, learning …
domains. However, when the available target domain data are scarce for training, learning …
Carlane: A lane detection benchmark for unsupervised domain adaptation from simulation to multiple real-world domains
B Stuhr, J Haselberger… - Advances in Neural …, 2022 - proceedings.neurips.cc
Abstract Unsupervised Domain Adaptation demonstrates great potential to mitigate domain
shifts by transferring models from labeled source domains to unlabeled target domains …
shifts by transferring models from labeled source domains to unlabeled target domains …
Class-wise Prototype Guided Alignment Network for Cross-Scene Hyperspectral Image Classification
In the past few years, there has been significant progress in hyperspectral image
classification (HSIC). However, when the trained classifier on the source scene is directly …
classification (HSIC). However, when the trained classifier on the source scene is directly …
Unexplainable explanations: Towards interpreting tSNE and UMAP embeddings
A Draganov, S Dohn - arXiv preprint arXiv:2306.11898, 2023 - arxiv.org
It has become standard to explain neural network latent spaces with attraction/repulsion
dimensionality reduction (ARDR) methods like tSNE and UMAP. This relies on the premise …
dimensionality reduction (ARDR) methods like tSNE and UMAP. This relies on the premise …
Exploiting inter-sample affinity for knowability-aware universal domain adaptation
Universal domain adaptation aims to transfer the knowledge of common classes from the
source domain to the target domain without any prior knowledge on the label set, which …
source domain to the target domain without any prior knowledge on the label set, which …
Revisiting unsupervised domain adaptation models: A smoothness perspective
Abstract Unsupervised Domain Adaptation (UDA) aims to leverage the labeled source data
and unlabeled target data to generalize better in the target domain. UDA methods utilize …
and unlabeled target data to generalize better in the target domain. UDA methods utilize …
A Virtual-Label-Based Hierarchical Domain Adaptation Method for Time-Series Classification
Unsupervised domain adaptation (UDA) is becoming a prominent solution for the domain-
shift problem in many time-series classification tasks. With sequence properties, time-series …
shift problem in many time-series classification tasks. With sequence properties, time-series …