Recent advances in optimal transport for machine learning
Recently, Optimal Transport has been proposed as a probabilistic framework in Machine
Learning for comparing and manipulating probability distributions. This is rooted in its rich …
Learning for comparing and manipulating probability distributions. This is rooted in its rich …
Lamda: Label matching deep domain adaptation
Deep domain adaptation (DDA) approaches have recently been shown to perform better
than their shallow rivals with better modeling capacity on complex domains (eg, image …
than their shallow rivals with better modeling capacity on complex domains (eg, image …
Stem: An approach to multi-source domain adaptation with guarantees
Abstract Multi-source Domain Adaptation (MSDA) is more practical but challenging than the
conventional unsupervised domain adaptation due to the involvement of diverse multiple …
conventional unsupervised domain adaptation due to the involvement of diverse multiple …
Your data is not perfect: Towards cross-domain out-of-distribution detection in class-imbalanced data
X Fang, A Easwaran, B Genest… - Expert Systems with …, 2025 - Elsevier
Out-of-distribution detection (OOD detection) aims to detect test samples drawn from a
distribution that is different from the training distribution, in order to prevent models trained …
distribution that is different from the training distribution, in order to prevent models trained …
Transformed distribution matching for missing value imputation
We study the problem of imputing missing values in a dataset, which has important
applications in many domains. The key to missing value imputation is to capture the data …
applications in many domains. The key to missing value imputation is to capture the data …
A unified wasserstein distributional robustness framework for adversarial training
It is well-known that deep neural networks (DNNs) are susceptible to adversarial attacks,
exposing a severe fragility of deep learning systems. As the result, adversarial training (AT) …
exposing a severe fragility of deep learning systems. As the result, adversarial training (AT) …
Distribution alignment optimization through neural collapse for long-tailed classification
A well-trained deep neural network on balanced datasets usually exhibits the Neural
Collapse (NC) phenomenon, which is an informative indicator of the model achieving good …
Collapse (NC) phenomenon, which is an informative indicator of the model achieving good …
MANNER: A variational memory-augmented model for cross domain few-shot named entity recognition
This paper focuses on the task of cross domain few-shot named entity recognition (NER),
which aims to adapt the knowledge learned from source domain to recognize named entities …
which aims to adapt the knowledge learned from source domain to recognize named entities …
Tuning multi-mode token-level prompt alignment across modalities
Advancements in prompt tuning of vision-language models have underscored their potential
in enhancing open-world visual concept comprehension. However, prior works only …
in enhancing open-world visual concept comprehension. However, prior works only …
Tidot: A teacher imitation learning approach for domain adaptation with optimal transport
Using the principle of imitation learning and the theory of optimal transport we propose in
this paper a novel model for unsupervised domain adaptation named Teacher Imitation …
this paper a novel model for unsupervised domain adaptation named Teacher Imitation …