paper-with-me

Papers

Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation

2023-11-22 · Junyu Gao, Xuan Yao, Changsheng Xu

The ability to accurately comprehend natural language instructions and navigate to the target location is essential for an embodied agent. Such agents are typically required to execute user instructions in an online manner, leading us to explore the use of unlabeled test samples for effective online model adaptation. However, for online Vision-and-Language Navigation (VLN), due to the intrinsic nature of inter-sample online instruction execution and intra-sample multi-step action decision, frequent updates can result in drastic changes in model parameters, while occasional updates can make the model ill-equipped to handle dynamically changing environments. Therefore, we propose a Fast-Slow Test-Time Adaptation (FSTTA) approach for online VLN by performing joint decomposition-accumulation analysis for both gradients and parameters in a unified framework. Extensive experiments show that our method obtains impressive performance gains on four popular benchmarks. Code is available at https://github.com/Feliciaxyao/ICML2024-FSTTA.

📄 PDF Abstract BibTeX arXiv:2311.13209

Code (1)

feliciaxyao/icml2024-fstta 공식 구현 pytorch

Tasks

NavigateTest-time AdaptationVision and Language Navigation

Similar Papers 제목 키워드 기반

Evaluation of Test-Time Adaptation Under Computational Time Constraints

2023-04-10 · Motasem Alfarra, Hani Itani, Alejandro Pardo, Shyma Alhuwaider 외

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 te…

Test-time Adaptation

SlowFast-SCI: Slow-Fast Deep Unfolding Learning for Spectral Compressive Imaging

2025-09-20 · Haijin Zeng, Xuan Lu, Yurong Zhang, Qiangqiang Shen 외 arxiv

Humans learn in two complementary ways: a slow, cumulative process that builds broad, general knowledge, and a fast, on-the-fly process that captures specific experiences. Existing deep-unfolding methods for spectral com…

Spectral ReconstructionTest-time AdaptationGeneral Knowledge

SloMo-Fast: Slow-Momentum and Fast-Adaptive Teachers for Source-Free Continual Test-Time Adaptation

2025-11-23 · Md Akil Raihan Iftee, Mir Sazzat Hossain, Rakibul Hasan Rajib, Tariq Iqbal 외 arxiv

Continual Test-Time Adaptation (CTTA) is crucial for deploying models in real-world applications with unseen, evolving target domains. Existing CTTA methods, however, often rely on source data or prototypes, limiting the…

Test-time Adaptation

Learning Fast and Slow for Online Time Series Forecasting

2022-02-23 · Quang Pham, Chenghao Liu, Doyen Sahoo, Steven C. H. Hoi

The fast adaptation capability of deep neural networks in non-stationary environments is critical for online time series forecasting. Successful solutions require handling changes to new and recurring patterns. However, …

Time SeriesTime Series AnalysisTime Series Forecasting

Slow and Fast Neurons Cooperate in Contextual Working Memory through Timescale Diversity

2025-06-09 · Tomoki Kurikawa

Neural systems process information across a broad range of intrinsic timescales, both within and across cortical areas. While such diversity is a hallmark of biological networks, its computational role in nonlinear infor…

Diversity