English
Related papers

Related papers: Training on Test Data with Bayesian Adaptation for…

200 papers

Domain adaptation is an important technique to alleviate performance degradation caused by domain shift, e.g., when training and test data come from different domains. Most existing deep adaptation methods focus on reducing domain shift by…

Machine Learning · Computer Science 2019-06-25 Jun Wen , Nenggan Zheng , Junsong Yuan , Zhefeng Gong , Changyou Chen

Deep neural networks often exhibit poor performance on data that is unlikely under the train-time data distribution, for instance data affected by corruptions. Previous works demonstrate that test-time adaptation to data shift, for instance…

Modern neural networks have proven to be powerful function approximators, providing state-of-the-art performance in a multitude of applications. They however fall short in their ability to quantify confidence in their predictions - this is…

Machine Learning · Statistics 2020-06-29 Alex J. Chan , Ahmed M. Alaa , Zhaozhi Qian , Mihaela van der Schaar

In supervised learning, the estimation of prediction error on unlabeled test data is an important task. Existing methods are usually built on the assumption that the training and test data are sampled from the same distribution, which is…

Methodology · Statistics 2022-09-30 Hui Xu , Robert Tibshirani

Neural networks make accurate predictions but often fail to provide reliable uncertainty estimates, especially under covariate distribution shifts between training and testing. To address this problem, we propose a Bayesian framework for…

Machine Learning · Statistics 2025-12-22 Yuli Slavutsky , David M. Blei

A common assumption in semi-supervised learning is that the labeled, unlabeled, and test data are drawn from the same distribution. However, this assumption is not satisfied in many applications. In many scenarios, the data is collected…

Information Theory · Computer Science 2022-02-25 Gholamali Aminian , Mahed Abroshan , Mohammad Mahdi Khalili , Laura Toni , Miguel R. D. Rodrigues

In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised…

Machine Learning · Computer Science 2020-07-03 Yu Sun , Xiaolong Wang , Zhuang Liu , John Miller , Alexei A. Efros , Moritz Hardt

Graph contrastive learning has shown great promise when labeled data is scarce, but large unlabeled datasets are available. However, it often does not take uncertainty estimation into account. We show that a variational Bayesian neural…

Machine Learning · Computer Science 2023-12-04 Alexander Möllers , Alexander Immer , Elvin Isufi , Vincent Fortuin

Test-time domain adaptation aims to adapt the model trained on source domains to unseen target domains using a few unlabeled images. Emerging research has shown that the label and domain information is separately embedded in the weight…

Computer Vision and Pattern Recognition · Computer Science 2024-01-18 Yanan Wu , Zhixiang Chi , Yang Wang , Konstantinos N. Plataniotis , Songhe Feng

Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal…

Machine Learning · Statistics 2019-10-29 Raanan Y. Rohekar , Yaniv Gurwicz , Shami Nisimov , Gal Novik

In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and…

Machine Learning · Computer Science 2022-05-12 Antonio-Javier Gallego , Jorge Calvo-Zaragoza , Robert B. Fisher

We propose a novel framework of the model specification test in regression using unlabeled test data. In many cases, we have conducted statistical inferences based on the assumption that we can correctly specify a model. However, it is…

Methodology · Statistics 2020-02-25 Masahiro Kato , Hikaru Kawarazaki

Class distribution plays an important role in learning deep classifiers. When the proportion of each class in the test set differs from the training set, the performance of classification nets usually degrades. Such a label distribution…

Image and Video Processing · Electrical Eng. & Systems 2022-07-12 Wenao Ma , Cheng Chen , Shuang Zheng , Jing Qin , Huimao Zhang , Qi Dou

In many real-world applications, researchers aim to deploy models trained in a source domain to a target domain, where obtaining labeled data is often expensive, time-consuming, or even infeasible. While most existing literature assumes…

Methodology · Statistics 2025-08-26 Seong-ho Lee , Yanyuan Ma , Jiwei Zhao

Bayesian neural networks (BNNs) promise improved generalization under covariate shift by providing principled probabilistic representations of epistemic uncertainty. However, weight-based BNNs often struggle with high computational…

Machine Learning · Statistics 2022-06-13 Trung Trinh , Markus Heinonen , Luigi Acerbi , Samuel Kaski

Modern image classifiers are very accurate, but the predictions come without uncertainty estimates. Conformal predictors provide uncertainty estimates by computing a set of classes containing the correct class with a user-specified…

Machine Learning · Computer Science 2023-06-06 Fatih Furkan Yilmaz , Reinhard Heckel

Amortized Bayesian inference (ABI) with neural networks can solve probabilistic inverse problems orders of magnitude faster than classical methods. However, ABI is not yet sufficiently robust for widespread and safe application. When…

Machine Learning · Statistics 2026-03-04 Aayush Mishra , Daniel Habermann , Marvin Schmitt , Stefan T. Radev , Paul-Christian Bürkner

Classifier predictions often rely on the assumption that new observations come from the same distribution as training data. When the underlying distribution changes, so does the optimal classification rule, and performance may degrade. We…

Methodology · Statistics 2021-09-01 Ciaran Evans , Max G'Sell

Deploying deep visual models can lead to performance drops due to the discrepancies between source and target distributions. Several approaches leverage labeled source data to estimate target domain accuracy, but accessing labeled source…

Computer Vision and Pattern Recognition · Computer Science 2023-07-20 JoonHo Lee , Jae Oh Woo , Hankyu Moon , Kwonho Lee

While many real-world data streams imply that they change frequently in a nonstationary way, most of deep learning methods optimize neural networks on training data, and this leads to severe performance degradation when dataset shift…

Machine Learning · Computer Science 2021-07-02 Wonju Lee , Seok-Yong Byun , Jooeun Kim , Minje Park , Kirill Chechil
‹ Prev 1 2 3 10 Next ›