PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation
- URL: http://arxiv.org/abs/2403.10650v1
- Date: Fri, 15 Mar 2024 19:35:10 GMT
- Title: PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation
- Authors: Sarthak Kumar Maharana, Baoming Zhang, Yunhui Guo,
- Abstract summary: Continual test-time adaptation (CTTA) directly adjusts a pre-trained source discriminative model to changing domains using test data.
We identify layers through the quantification of model prediction uncertainty without relying on pseudo-labels.
We conduct extensive image classification experiments on CIFAR-10C, CIFAR-100C, and ImageNet-C and demonstrate the efficacy of our method.
- Score: 6.181548939188321
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Real-world vision models in dynamic environments face rapid shifts in domain distributions, leading to decreased recognition performance. Continual test-time adaptation (CTTA) directly adjusts a pre-trained source discriminative model to these changing domains using test data. A highly effective CTTA method involves applying layer-wise adaptive learning rates, and selectively adapting pre-trained layers. However, it suffers from the poor estimation of domain shift and the inaccuracies arising from the pseudo-labels. In this work, we aim to overcome these limitations by identifying layers through the quantification of model prediction uncertainty without relying on pseudo-labels. We utilize the magnitude of gradients as a metric, calculated by backpropagating the KL divergence between the softmax output and a uniform distribution, to select layers for further adaptation. Subsequently, for the parameters exclusively belonging to these selected layers, with the remaining ones frozen, we evaluate their sensitivity in order to approximate the domain shift, followed by adjusting their learning rates accordingly. Overall, this approach leads to a more robust and stable optimization than prior approaches. We conduct extensive image classification experiments on CIFAR-10C, CIFAR-100C, and ImageNet-C and demonstrate the efficacy of our method against standard benchmarks and prior methods.
Related papers
- Enhanced Online Test-time Adaptation with Feature-Weight Cosine Alignment [7.991720491452191]
Online Test-Time Adaptation (OTTA) has emerged as an effective strategy to handle distributional shifts.
This paper introduces a novel cosine alignment optimization approach with a dual-objective loss function.
Our method outperforms state-of-the-art techniques and sets a new benchmark in multiple datasets.
arXiv Detail & Related papers (2024-05-12T05:57:37Z) - Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation [49.827306773992376]
Continual Test-Time Adaptation (CTTA) is proposed to migrate a source pre-trained model to continually changing target distributions.
Our proposed method attains state-of-the-art performance in both classification and segmentation CTTA tasks.
arXiv Detail & Related papers (2023-12-19T15:34:52Z) - Layer-wise Auto-Weighting for Non-Stationary Test-Time Adaptation [40.03897994619606]
We introduce a layer-wise auto-weighting algorithm for continual and gradual TTA.
We propose an exponential min-max scaler to make certain layers nearly frozen while mitigating outliers.
Experiments on CIFAR-10C, CIFAR-100C, and ImageNet-C show our method outperforms conventional continual and gradual TTA approaches.
arXiv Detail & Related papers (2023-11-10T03:54:40Z) - Effective Restoration of Source Knowledge in Continual Test Time
Adaptation [44.17577480511772]
This paper introduces an unsupervised domain change detection method that is capable of identifying domain shifts in dynamic environments.
By restoring the knowledge from the source, it effectively corrects the negative consequences arising from the gradual deterioration of model parameters.
We perform extensive experiments on benchmark datasets to demonstrate the superior performance of our method compared to state-of-the-art adaptation methods.
arXiv Detail & Related papers (2023-11-08T19:21:48Z) - Domain Generalization Guided by Gradient Signal to Noise Ratio of
Parameters [69.24377241408851]
Overfitting to the source domain is a common issue in gradient-based training of deep neural networks.
We propose to base the selection on gradient-signal-to-noise ratio (GSNR) of network's parameters.
arXiv Detail & Related papers (2023-10-11T10:21:34Z) - Variational Classification [51.2541371924591]
We derive a variational objective to train the model, analogous to the evidence lower bound (ELBO) used to train variational auto-encoders.
Treating inputs to the softmax layer as samples of a latent variable, our abstracted perspective reveals a potential inconsistency.
We induce a chosen latent distribution, instead of the implicit assumption found in a standard softmax layer.
arXiv Detail & Related papers (2023-05-17T17:47:19Z) - MCDAL: Maximum Classifier Discrepancy for Active Learning [74.73133545019877]
Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition.
We propose in this paper a novel active learning framework that we call Maximum Discrepancy for Active Learning (MCDAL)
In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them.
arXiv Detail & Related papers (2021-07-23T06:57:08Z) - Selective Pseudo-Labeling with Reinforcement Learning for
Semi-Supervised Domain Adaptation [116.48885692054724]
We propose a reinforcement learning based selective pseudo-labeling method for semi-supervised domain adaptation.
We develop a deep Q-learning model to select both accurate and representative pseudo-labeled instances.
Our proposed method is evaluated on several benchmark datasets for SSDA, and demonstrates superior performance to all the comparison methods.
arXiv Detail & Related papers (2020-12-07T03:37:38Z) - Adaptive Gradient Method with Resilience and Momentum [120.83046824742455]
We propose an Adaptive Gradient Method with Resilience and Momentum (AdaRem)
AdaRem adjusts the parameter-wise learning rate according to whether the direction of one parameter changes in the past is aligned with the direction of the current gradient.
Our method outperforms previous adaptive learning rate-based algorithms in terms of the training speed and the test error.
arXiv Detail & Related papers (2020-10-21T14:49:00Z)
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.