Continual Test-Time Domain Adaptation

• URL: http://arxiv.org/abs/2203.13591v1
• Date: Fri, 25 Mar 2022 11:42:02 GMT
• Title: Continual Test-Time Domain Adaptation
• Authors: Qin Wang, Olga Fink, Luc Van Gool, Dengxin Dai
• Abstract summary: Test-time domain adaptation aims to adapt a source pre-trained model to a target domain without using any source data. CoTTA is easy to implement and can be readily incorporated in off-the-shelf pre-trained models.
• Score: 94.51284735268597
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Test-time domain adaptation aims to adapt a source pre-trained model to a target domain without using any source data. Existing works mainly consider the case where the target domain is static. However, real-world machine perception systems are running in non-stationary and continually changing environments where the target domain distribution can change over time. Existing methods, which are mostly based on self-training and entropy regularization, can suffer from these non-stationary environments. Due to the distribution shift over time in the target domain, pseudo-labels become unreliable. The noisy pseudo-labels can further lead to error accumulation and catastrophic forgetting. To tackle these issues, we propose a continual test-time adaptation approach~(CoTTA) which comprises two parts. Firstly, we propose to reduce the error accumulation by using weight-averaged and augmentation-averaged predictions which are often more accurate. On the other hand, to avoid catastrophic forgetting, we propose to stochastically restore a small part of the neurons to the source pre-trained weights during each iteration to help preserve source knowledge in the long-term. The proposed method enables the long-term adaptation for all parameters in the network. CoTTA is easy to implement and can be readily incorporated in off-the-shelf pre-trained models. We demonstrate the effectiveness of our approach on four classification tasks and a segmentation task for continual test-time adaptation, on which we outperform existing methods. Our code is available at \url{https://qin.ee/cotta}.

Related papers

• Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation [62.889835139583965]
  We tackle the problem of source-free unsupervised domain adaptation (SFUDA) for 3D semantic segmentation. It amounts to performing domain adaptation on an unlabeled target domain without any access to source data. A common issue with existing SFUDA approaches is that performance degrades after some training time.
  arXiv  Detail & Related papers  (2024-09-06T17:13:14Z)
• Backpropagation-free Network for 3D Test-time Adaptation [42.469853469556966]
  Test-Time Adaptation (TTA) methods tend to apply computationally heavy and memory-intensive backpropagation-based approaches. Here, we propose a novel method that uses a backpropagation-free approach for TTA for the specific case of 3D data.
  arXiv  Detail & Related papers  (2024-03-27T10:50:24Z)
• Mitigating the Bias in the Model for Continual Test-Time Adaptation [32.33057968481597]
  Continual Test-Time Adaptation (CTA) is a challenging task that aims to adapt a source pre-trained model to continually changing target domains. We find that a model shows highly biased predictions as it constantly adapts to the chaining distribution of the target data. This paper mitigates this issue to improve performance in the CTA scenario.
  arXiv  Detail & Related papers  (2024-03-02T23:37:16Z)
• Unraveling Batch Normalization for Realistic Test-Time Adaptation [22.126177142716188]
  This paper delves into the problem of mini-batch degradation. By unraveling batch normalization, we discover that the inexact target statistics largely stem from the substantially reduced class diversity in batch. We introduce a straightforward tool, Test-time Exponential Moving Average (TEMA), to bridge the class diversity gap between training and testing batches.
  arXiv  Detail & Related papers  (2023-12-15T01:52:35Z)
• Few-Shot Adaptation of Pre-Trained Networks for Domain Shift [17.123505029637055]
  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 deployed in new target environments with streaming data to mitigate such performance degradation. We propose a framework for few-shot domain adaptation to address the practical challenges of data-efficient adaptation.
  arXiv  Detail & Related papers  (2022-05-30T16:49:59Z)
• Source-Free Domain Adaptation via Distribution Estimation [106.48277721860036]
  Domain Adaptation aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain whose data distributions are different. Recently, Source-Free Domain Adaptation (SFDA) has drawn much attention, which tries to tackle domain adaptation problem without using source data. In this work, we propose a novel framework called SFDA-DE to address SFDA task via source Distribution Estimation.
  arXiv  Detail & Related papers  (2022-04-24T12:22:19Z)
• Target and Task specific Source-Free Domain Adaptive Image Segmentation [73.78898054277538]
  We propose a two-stage approach for source-free domain adaptive image segmentation. We focus on generating target-specific pseudo labels while suppressing high entropy regions. In the second stage, we focus on adapting the network for task-specific representation.
  arXiv  Detail & Related papers  (2022-03-29T17:50:22Z)
• Distribution Mismatch Correction for Improved Robustness in Deep Neural Networks [86.42889611784855]
  normalization methods increase the vulnerability with respect to noise and input corruptions. We propose an unsupervised non-parametric distribution correction method that adapts the activation distribution of each layer. In our experiments, we empirically show that the proposed method effectively reduces the impact of intense image corruptions.
  arXiv  Detail & Related papers  (2021-10-05T11:36:25Z)
• Adaptive Risk Minimization: Learning to Adapt to Domain Shift [109.87561509436016]
  A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. In this work, we consider the problem setting of domain generalization, where the training data are structured into domains and there may be multiple test time shifts. We introduce the framework of adaptive risk minimization (ARM), in which models are directly optimized for effective adaptation to shift by learning to adapt on the training domains.
  arXiv  Detail & Related papers  (2020-07-06T17:59:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.