Machine learning methods strive to acquire a robust model during training that can generalize well to test samples, even under distribution shifts. However, these methods often suffer from a performance drop due to unknown test distributions. Test-time adaptation (TTA), an emerging paradigm, has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions. Recent progress in this paradigm highlights the significant benefits of utilizing unlabeled data for training self-adapted models prior to inference. In this survey, we divide TTA into several distinct categories, namely, test-time (source-free) domain adaptation, test-time batch adaptation, online test-time adaptation, and test-time prior adaptation. For each category, we provide a comprehensive taxonomy of advanced algorithms, followed by a discussion of different learning scenarios. Furthermore, we analyze relevant applications of TTA and discuss open challenges and promising areas for future research. A comprehensive list of TTA methods can be found at \url{https://github.com/tim-learn/awesome-test-time-adaptation}.

A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts

To enable video models to be applied seamlessly across video tasks in different environments, various Video Unsupervised Domain Adaptation (VUDA) methods have been proposed to improve the robustness and transferability of video models. Despite improvements made in model robustness, these VUDA methods require access to both source data and source model parameters for adaptation, raising serious data privacy and model portability issues. To cope with the above concerns, this paper ﬁrstly formulates Black-box Video Domain Adaptation (BVDA) as a more realistic yet challenging scenario where the source video model is provided only as a black-box predictor. While a few methods for Black-box Domain Adaptation (BDA) are proposed in image domain, these methods cannot apply to video domain since video modality has more complicated temporal features that are harder to align. To address BVDA, we propose a novel Endo and eXo-TEmporal Regularized Network (EXTERN) by applying mask-to-mix strategies and video-tailored regularizations: endo-temporal regularization and exo-temporal regularization, performed across both clip and temporal features, while distilling knowledge from the predictions obtained from the black-box predictor. Empirical results demonstrate the state-of-the-art performance of EXTERN across various cross-domain closed-set and partial-set action recognition benchmarks, which even sur-passed most existing video domain adaptation methods with source

EXTERN: Leveraging Endo-Temporal Regularization for Black-box Video Domain Adaptation

To enable video models to be applied seamlessly across video tasks in different environments, various Video Unsupervised Domain Adaptation (VUDA) methods have been proposed to improve the robustness and transferability of video models. Despite improvements made in model robustness, these VUDA methods require access to both source data and source model parameters for adaptation, raising serious data privacy and model portability issues. To cope with the above concerns, this paper ﬁrstly formulates Black-box Video Domain Adaptation (BVDA) as a more realistic yet challenging scenario where the source video model is provided only as a black-box predictor. While a few methods for Black-box Domain Adaptation (BDA) are proposed in image domain, these methods cannot apply to video domain since video modality has more complicated temporal features that are harder to align. To address BVDA, we propose a novel Endo and eXo-TEmporal Regularized Network (EXTERN) by applying mask-to-mix strategies and video-tailored regularizations: endo-temporal regularization and exo-temporal regularization, performed across both clip and temporal features, while distilling knowledge from the predictions obtained from the black-box predictor. Empirical results demonstrate the state-of-the-art performance of EXTERN across various cross-domain closed-set and partial-set action recognition benchmarks, which even sur-passed most existing video domain adaptation methods with

pdf/leveraging-endo-and-exo-temporal-regularization-for-black-3w4xigbm.pdf

Leveraging Endo- and Exo-Temporal Regularization for Black-box Video Domain Adaptation

Deep learning has achieved excellent performance in computer vision tasks, like image recognition, natural language processing, etc. However, in real-world applications, special circumstances brought about by the external world may create domain bias caused by distribution discrepancy between training and testing data, leading to degrading model performance. For example, when auto-driving meets hazy weather, the model performance will drop significantly. In this paper, we explore to solve this problem by utilizing modern Domain Adaptation (DA) methods, which generalizes from the source domain to the target domain by minimizing the distribution difference caused by dataset bias. We firstly propose the cross-domain haze image datasets and benchmark the five classic DA methods. The experiments show that DA methods can mitigate the negative effect of haze and significantly improves the model performance for visual recognition.

Improving Hazy Image Recognition by Unsupervised Domain Adaptation

. Video-based Unsupervised Domain Adaptation (VUDA) methods improve the robustness of video models, enabling them to be applied to action recognition tasks across diﬀerent environments. However, these methods require constant access to source data during the adaptation process. Yet in many real-world applications, subjects and scenes in the source video domain should be irrelevant to those in the target video domain. With the increasing emphasis on data privacy, such methods that require source data access would raise serious privacy issues. Therefore, to cope with such concern, a more practical domain adaptation scenario is formulated as the Source-Free Video-based Domain Adaptation (SFVDA). Though there are a few methods for Source-Free Domain Adaptation (SFDA) on image data, these methods yield de-generating performance in SFVDA due to the multi-modality nature of videos, with the existence of additional temporal features. In this paper, we propose a novel Attentive Temporal Consistent Network (ATCoN) to address SFVDA by learning temporal consistency, guaranteed by two novel consistency objectives, namely feature consistency and source prediction consistency, performed across local temporal features. ATCoN further constructs eﬀective overall temporal features by attending to local temporal features based on prediction conﬁdence. Empirical results demonstrate the state-of-the-art performance of ATCoN across various cross-domain action recognition benchmarks.

Learning Temporal Consistency for Source-Free Video Domain Adaptation

Elderly fall detection aims at automatically detecting fall actions, a major public health problem for the elderly. Existing fall detection methods are cost-ineffective - a satisfactory performance is commonly traded by high costs in device access/deployment and positive record acquirement. In this paper, we set out to devise a WiFi-based elderly fall detection approach in a cost-effective manner - being high in detection accuracy, and low in costs of device access and positively -annotated data. Specifically, our system builds on commercial WiFi, a ubiquitously available device, which greatly saves device access and deployment costs. To extract the nuanced and implicit features due to the low signal-to-noise ratio of WiFi signals, we propose symmetry Transformer networks, a variant of Transformer to facilitate better feature representation learning. Meanwhile, to overcome the positive scarcity and low inter-environment transferability brought by Transformer, we propose a novel two-stage training scheme, where the representation learning is performed in an unsupervised manner. This unveils a transferability property that reduces the requirements on positive instances in training the resulting model. Empirical evaluation demonstrates our cost-effective desideratum while achieving superior performance compared with state-of-the-art models.

Cost-effective Elderly Fall Detection with Symmetry Transformer Networks

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Wu Min

Author Tools

Chat about Author

Papers

Learning Temporal Consistency for Source-Free Video Domain Adaptation

Cost-effective Elderly Fall Detection with Symmetry Transformer Networks