paper-with-me

Papers

Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation

2024-07-12 · Zhilin Zhu, Xiaopeng Hong, Zhiheng Ma, Weijun Zhuang, Yaohui Ma, Yong Dai, YaoWei Wang

Continual Test-Time Adaptation (CTTA) involves adapting a pre-trained source model to continually changing unsupervised target domains. In this paper, we systematically analyze the challenges of this task: online environment, unsupervised nature, and the risks of error accumulation and catastrophic forgetting under continual domain shifts. To address these challenges, we reshape the online data buffering and organizing mechanism for CTTA. We propose an uncertainty-aware buffering approach to identify and aggregate significant samples with high certainty from the unsupervised, single-pass data stream. Based on this, we propose a graph-based class relation preservation constraint to overcome catastrophic forgetting. Furthermore, a pseudo-target replay objective is used to mitigate error accumulation. Extensive experiments demonstrate the superiority of our method in both segmentation and classification CTTA tasks. Code is available at https://github.com/z1358/OBAO.

📄 PDF Abstract BibTeX arXiv:2407.09367

Code (1)

z1358/obao 공식 구현 pytorch

Tasks

Test-time Adaptation

Similar Papers 제목 키워드 기반

No Labels, No Look-Ahead: Unsupervised Online Video Stabilization with Classical Priors

2026-02-26 · Tao Liu, Gang Wan, Kan Ren, Shibo Wen arxiv

We propose a new unsupervised framework for online video stabilization. Unlike methods based on deep learning that require paired stable and unstable datasets, our approach instantiates the classical stabilization pipeli…

Self-Organizing Dual-Buffer Adaptive Clustering Experience Replay (SODACER) for Safe Reinforcement Learning in Optimal Control

2026-01-10 · Roya Khalili Amirabadi, Mohsen Jalaeian Farimani, Omid Solaymani Fard arxiv

This paper proposes a novel reinforcement learning framework, named Self-Organizing Dual-buffer Adaptive Clustering Experience Replay (SODACER), designed to achieve safe and scalable optimal control of nonlinear systems.…

Reinforcement Learning

Foundation Models for Cross-Domain EEG Analysis Application: A Survey

2025-08-21 · Hongqi Li, Yitong Chen, Yujuan Wang, Weihang Ni 외 arxiv

Electroencephalography (EEG) analysis stands at the forefront of neuroscience and artificial intelligence research, where foundation models are reshaping the traditional EEG analysis paradigm by leveraging their powerful…

Domain GeneralizationEeg Decoding

Predicting nonlinear reshaping of periodic signals in optical fibre with a neural network

2023-03-16 · Sonia Boscolo, J. M. Dudley, Christophe Finot

We deploy a supervised machine-learning model based on a neural network to predict the temporal and spectral reshaping of a simple sinusoidal modulation into a pulse train having a comb structure in the frequency domain,…

Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference

2023-03-10 · Haiyang Huang, Newsha Ardalani, Anna Sun, Liu Ke 외

Mixture-of-Experts (MoE) models have gained popularity in achieving state-of-the-art performance in a wide range of tasks in computer vision and natural language processing. They effectively expand the model capacity whi…

CPUDecoderGPULanguage Modeling+3