This paper proposes a novel online evaluation protocol for Test Time Adaptation (TTA) methods, which penalizes slower methods by providing them with fewer samples for adaptation. TTA methods leverage unlabeled data at test time to adapt to distribution shifts. Although many effective methods have been proposed, their impressive performance usually comes at the cost of significantly increased computation budgets. Current evaluation protocols overlook the effect of this extra computation cost, affecting their real-world applicability. To address this issue, we propose a more realistic evaluation protocol for TTA methods, where data is received in an online fashion from a constant-speed data stream, thereby accounting for the method's adaptation speed. We apply our proposed protocol to benchmark several TTA methods on multiple datasets and scenarios. Extensive experiments show that, when accounting for inference speed, simple and fast approaches can outperform more sophisticated but slower methods. For example, SHOT from 2020, outperforms the state-of-the-art method SAR from 2023 in this setting. Our results reveal the importance of developing practical TTA methods that are both accurate and efficient.
A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
Center for Research on Intelligent Perception and Computing（智能感知与计算研究中心）；State Key Laboratory of Multimodal Artificial Intelligence Systems（多模态人工智能系统国家重点实验室）；CASIA（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Nanjing University（南京大学）
Tsinghua University（清华大学）；Tencent TEG AI（腾讯技术工程事业群人工智能实验室）；OPPO research institute（OPPO研究院）；Peng Cheng Laboratory（鹏城实验室）
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 to improving adaptation performance. However, we find that two unfavorable defects are concealed in the prevalent adaptation methodologies like test-time batch normalization (BN) and self-learning. First, we reveal that the normalization statistics in test-time BN are completely affected by the currently received test samples, resulting in inaccurate estimate…
In this paper, our goal is to adapt a pre-trained convolutional neural network to domain shifts at test time. We do so continually with the incoming stream of test batches, without labels. The existing literature mostly operates on artificial shifts obtained via adversarial perturbations of a test image. Motivated by this, we evaluate the state of the art on two realistic and challenging sources of domain shifts, namely contextual and semantic shifts. Contextual shifts correspond to the environment types, for example, a model pre-trained on indoor context has to adapt to the outdoor context on…
Back to the Source: Diffusion-Driven Test-Time Adaptation
Shanghai Jiao Tong University（上海交通大学）；The University of Hong Kong（香港大学）；University of California, Berkeley（加州大学伯克利分校）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；DeepMind（深度思维）
Qualcomm AI Research（高通AI研究院）；Qualcomm Technologies, Inc.（高通技术公司）；Nanjing University of Science and Technology（南京理工大学）
In video segmentation, generating temporally consistent results across frames is as important as achieving frame-wise accuracy. Existing methods rely either on optical flow regularization or fine-tuning with test data to attain temporal consistency. However, optical flow is not always avail-able and reliable. Besides, it is expensive to compute. Fine-tuning the original model in test time is cost sensitive. This paper presents an efficient, intuitive, and unsupervised online adaptation method, AuxAdapt, for improving the temporal consistency of most neural network models. It does not require o…
Univ Lyon（里昂大学）；Ecole Centrale de Lyon（里昂中央理工学院）；CNRS（法国国家科学研究中心）；INSA Lyon（里昂国立应用科学学院）；Univ Claude Bernard Lyon 1（里昂第一大学克洛德·贝尔纳）；Univ Louis Lumière Lyon 2（里昂第二大学路易·卢米埃尔）；Thales LAS France（泰雷兹LAS法国公司）
Deep neural networks often fail to generalize outside of their training distribution, in particular when only a single data domain is available during training. While test-time adaptation has yielded encouraging results in this setting, we argue that, to reach further improvements, these approaches should be combined with training procedure modifications aiming to learn a more diverse set of patterns. Indeed, test-time adaptation methods usually have to rely on a limited representation because of the shortcut learning phenomenon: only a subset of the available predictive patterns is learned wi…
Idiap Research Institute（伊迪亚普研究所）；EPFL（洛桑联邦理工学院）；University of Geneva（日内瓦大学）
Data samples generated by several real world processes are dynamic in nature \textit{i.e.}, their characteristics vary with time. Thus it is not possible to train and tackle all possible distributional shifts between training and inference, using the host of transfer learning methods in literature. In this paper, we tackle this problem of adapting to domain shift at inference time \textit{i.e.}, we do not change the training process, but quickly adapt the model at test-time to handle any domain shift. For this, we propose to enforce consistency of predictions of data sampled in the vicinity of…
A model must adapt itself to generalize to new and different data during testing. In this setting of fully test-time adaptation the model has only the test data and its own parameters. We propose to adapt by test entropy minimization (tent): we optimize the model for confidence as measured by the entropy of its predictions. Our method estimates normalization statistics and optimizes channel-wise affine transformations to update online on each batch. Tent reduces generalization error for image classification on corrupted ImageNet and CIFAR-10/100 and reaches a new state-of-the-art error on Imag…
Classical machine learning assumes that the training and test sets come from the same distributions. Therefore, a model learned from the labeled training data is expected to perform well on the test data. However, This assumption may not always hold in real-world applications where the training and the test data fall from different distributions, due to many factors, e.g., collecting the training and test sets from different sources, or having an out-dated training set due to the change of data over time. In this case, there would be a discrepancy across domain distributions, and naively apply…
University of Southern California（南加州大学）；Facebook AI
We present a simple and effective way to estimate the batch-norm statistics during test time, to fast adapt a source model to target test samples. Known as Test-Time Adaptation, most prior works studying this task follow two assumptions in their evaluation where (1) test samples come together as a large batch, and (2) all from a single test distribution. However, in practice, these two assumptions may not stand, the reasons for which we propose two new evaluation settings where batch sizes are arbitrary and multiple distributions are considered. Unlike the previous methods that require a large…
Test-time adaptation methods have been gaining attention recently as a practical solution for addressing source-to-target domain gaps by gradually updating the model without requiring labels on the target data. In this paper, we propose a method of test-time adaptation for category-level object pose estimation called TTA-COPE. We design a pose ensemble approach with a self-training loss using pose-aware confidence. Unlike previous unsupervised domain adaptation methods for category-level object pose estimation, our approach processes the test data in a sequential, online manner, and it does no…
Southern University of Science and Technology（南方科技大学）；Huawei Technologies Co., Ltd.（华为技术有限公司）；Pengcheng Laboratory（鹏城实验室）
Fully test-time adaptation aims to adapt the network model based on sequential analysis of input samples during the inference stage to address the cross-domain performance degradation problem of deep neural networks. We take inspiration from the biological plausibility learning where the neuron responses are tuned based on a local synapse-change procedure and activated by competitive lateral inhibition rules. Based on these feed-forward learning rules, we design a soft Hebbian learning process which provides an unsupervised and effective mechanism for online adaptation. We observe that the per…
Convolutional neural networks trained on publicly available medical imaging datasets (source domain) rarely generalise to different scanners or acquisition protocols (target domain). This motivates the active field of domain adaptation. While some approaches to the problem require labeled data from the target domain, others adopt an unsupervised approach to domain adaptation (UDA). Evaluating UDA methods consists of measuring the model's ability to generalise to unseen data in the target domain. In this work, we argue that this is not as useful as adapting to the test set directly. We therefor…
Scale-aware Test-time Click Adaptation for Pulmonary Nodule and Mass Segmentation
Wuhan University（武汉大学）；Artificial Intelligence Institute of Wuhan University（武汉大学人工智能研究院）；Swiss Federal Institute of Technology Lausanne (EPFL)（洛桑联邦理工学院（EPFL））；Dianei Technology（点内科技）
We consider a setting that a model needs to adapt to a new domain under distribution shifts, given that only unlabeled test samples from the new domain are accessible at test time. A common idea in most of the related works is constructing pseudo-labels for the unlabeled test samples and applying gradient descent (GD) to a loss function with the pseudo-labels. Recently, \cite{GSRK22} propose conjugate labels, which is a new kind of pseudo-labels for self-training at test time. They empirically show that the conjugate label outperforms other ways of pseudo-labeling on many domain adaptation ben…
Test-time adaptation (TTA) is an emerging paradigm that addresses distributional shifts between training and testing phases without additional data acquisition or labeling cost; only unlabeled test data streams are used for continual model adaptation. Previous TTA schemes assume that the test samples are independent and identically distributed (i.i.d.), even though they are often temporally correlated (non-i.i.d.) in application scenarios, e.g., autonomous driving. We discover that most existing TTA methods fail dramatically under such scenarios. Motivated by this, we present a new test-time a…
Conformal Uncertainty Indicator for Continual Test-Time Adaptation
New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所新模式识别实验室）；China Nuclear Power Engineering Co., LTD（中国核电工程有限公司）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；School of Computer Science & Engineering, LinYi University（临沂大学计算机科学与工程学院）；School of Electric & Information Engineering, Suzhou University of Science and Technology（苏州科技大学电子与信息工程学院）
Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation
Poznan University of Technology（波兹南理工大学）；IDEAS NCBR；NASK - National Research Institute（NASK国家研究所）；Gdańsk University of Technology（格但斯克理工大学）；Graz University of Technology（格拉茨理工大学）
University of Amsterdam（阿姆斯特丹大学）；United Imaging Healthcare, Co., Ltd.（联影医疗技术集团有限公司）；Inception Institute of Artificial Intelligence（人工智能初创研究所）
In this paper, we propose energy-based sample adaptation at test time for domain generalization. Where previous works adapt their models to target domains, we adapt the unseen target samples to source-trained models. To this end, we design a discriminative energy-based model, which is trained on source domains to jointly model the conditional distribution for classification and data distribution for sample adaptation. The model is optimized to simultaneously learn a classifier and an energy function. To adapt target samples to source distributions, we iteratively update the samples by energy m…
