paper-with-me

Papers

Temporal Test-Time Adaptation with State-Space Models

2024-07-17 · Mona Schirmer, Dan Zhang, Eric Nalisnick

Distribution shifts between training and test data are inevitable over the lifecycle of a deployed model, leading to performance decay. Adapting a model on test samples can help mitigate this drop in performance. However, most test-time adaptation methods have focused on synthetic corruption shifts, leaving a variety of distribution shifts underexplored. In this paper, we focus on distribution shifts that evolve gradually over time, which are common in the wild but challenging for existing methods, as we show. To address this, we propose STAD, a probabilistic state-space model that adapts a deployed model to temporal distribution shifts by learning the time-varying dynamics in the last set of hidden features. Without requiring labels, our model infers time-evolving class prototypes that act as a dynamic classification head. Through experiments on real-world temporal distribution shifts, we show that our method excels in handling small batch sizes and label shift.

📄 PDF Abstract BibTeX arXiv:2407.12492

Code (0)

등록된 구현이 없습니다.

Tasks

State Space ModelsTest-time Adaptation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Focus 설명 없음

Similar Papers 제목 키워드 기반

SPACE: SPike-Aware Consistency Enhancement for Test-Time Adaptation in Spiking Neural Networks

2025-04-03 · Xinyu Luo, Kecheng Chen, Pao-Sheng Vincent Sun, Chris Xing Tian 외

Spiking Neural Networks (SNNs), as a biologically plausible alternative to Artificial Neural Networks (ANNs), have demonstrated advantages in terms of energy efficiency, temporal processing, and biological plausibility. …

Test-time Adaptation

Test-Time Adaptation for Generalizable Task Progress Estimation

2025-06-11 · Christos Ziakas, Alessandra Russo

We propose a test-time adaptation method that enables a progress estimation model to adapt online to the visual and temporal context of test trajectories by optimizing a learned self-supervised objective. To this end, we…

In-Context LearningMeta-LearningTest-time Adaptation

Temporal Structure Matters for Efficient Test-Time Adaptation in Wearable Human Activity Recognition

2026-05-06 · Zishu Zhou, Zaipeng Xie, Xuanyao Jie arxiv

Wearable human activity recognition (WHAR) models often suffer from performance degradation under real-world cross-user distribution shifts. Test-time adaptation (TTA) mitigates this degradation by adapting models online…

Human Activity RecognitionTest-time Adaptation

AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation

2021-10-24 · Yizhe Zhang, Shubhankar Borse, Hong Cai, Fatih Porikli

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…

Optical Flow EstimationSegmentationSemantic SegmentationTest-time Adaptation+2

STEPS: A Temporal Smooth Error Propagation Solver on the Manifolds for Test-Time Adaptation in Time Series Forecasting

2026-05-08 · Jiaqi Liu, Yifan Ouyang, Zhifei Song, Sim Kuan Goh 외 arxiv

Test-Time Adaptation (TTA) aims to improve time series forecasting under distribution shifts by using limited observations revealed during inference. However, forecasting TTA must operate in a source-free online setting,…

Time Series ForecastingTest-time Adaptation