Related papers: Test-time Batch Statistics Calibration for Covaria…
Deep neural networks often suffer the data distribution shift between training and testing, and the batch statistics are observed to reflect the shift. In this paper, targeting of alleviating distribution shift in test time, we revisit the…
Deep neural networks have useful applications in many different tasks, however their performance can be severely affected by changes in the data distribution. For example, in the biomedical field, their performance can be affected by…
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…
Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates…
Test-Time Adaptation aims to adapt source domain model to testing data at inference stage with success demonstrated in adapting to unseen corruptions. However, these attempts may fail under more challenging real-world scenarios. Existing…
Normalization is a pre-processing step that converts the data into a more usable representation. As part of the deep neural networks (DNNs), the batch normalization (BN) technique uses normalization to address the problem of internal…
Deep networks are prone to performance degradation when there is a domain shift between the source (training) data and target (test) data. Recent test-time adaptation methods update batch normalization layers of pre-trained source models…
This paper proposes a novel batch normalization strategy for test-time adaptation. Recent test-time adaptation methods heavily rely on the modified batch normalization, i.e., transductive batch normalization (TBN), which calculates the mean…
Covariate shift has been shown to sharply degrade both predictive accuracy and the calibration of uncertainty estimates for deep learning models. This is worrying, because covariate shift is prevalent in a wide range of real world…
While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- Internal Covariate Shift-- the current solution has certain drawbacks. Specifically, BN depends on batch statistics…
In this paper, we propose a novel domain adaptation method for the source-free setting. In this setting, we cannot access source data during adaptation, while unlabeled target data and a model pretrained with source data are given. Due to…
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…
Fully test-time adaptation aims at adapting a pre-trained model to the test stream during real-time inference, which is urgently required when the test distribution differs from the training distribution. Several efforts have been devoted…
Despite recent advancements in deep learning, deep neural networks continue to suffer from performance degradation when applied to new data that differs from training data. Test-time adaptation (TTA) aims to address this challenge by…
This paper proposes a novel test-time adaptation strategy that adjusts the model pre-trained on the source domain using only unlabeled online data from the target domain to alleviate the performance degradation due to the distribution shift…
While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- \textit{Internal Covariate Shift}-- the current solution has certain drawbacks. For instance, BN depends on batch…
Test-time adaptation (TTA) aims to adapt a pre-trained model to the target domain in a batch-by-batch manner during inference. While label distributions often exhibit imbalances in real-world scenarios, most previous TTA approaches…
Existing calibration algorithms address the problem of covariate shift via unsupervised domain adaptation. However, these methods suffer from the following limitations: 1) they require unlabeled data from the target domain, which may not be…
Given a model trained on source data, Test-Time Adaptation (TTA) enables adaptation and inference in test data streams with domain shifts from the source. Current methods predominantly optimize the model for each incoming test data batch…
Despite progress, deep neural networks still suffer performance declines under distribution shifts between training and test domains, leading to a substantial decrease in Quality of Experience (QoE) for multimedia applications. Existing…