paper-with-me

홈 › Papers

Maintain Plasticity in Long-timescale Continual Test-time Adaptation

2024-12-28 · Yanshuo Wang, Xuesong Li, Jinguang Tong, Jie Hong, Jun Lan, Weiqiang Wang, Huijia Zhu, Haoxing Chen

Continual test-time domain adaptation (CTTA) aims to adjust pre-trained source models to perform well over time across non-stationary target environments. While previous methods have made considerable efforts to optimize the adaptation process, a crucial question remains: can the model adapt to continually-changing environments with preserved plasticity over a long time? The plasticity refers to the model's capability to adjust predictions in response to non-stationary environments continually. In this work, we explore plasticity, this essential but often overlooked aspect of continual adaptation to facilitate more sustained adaptation in the long run. First, we observe that most CTTA methods experience a steady and consistent decline in plasticity during the long-timescale continual adaptation phase. Moreover, we find that the loss of plasticity is strongly associated with the change in label flip. Based on this correlation, we propose a simple yet effective policy, Adaptive Shrink-Restore (ASR), towards preserving the model's plasticity. In particular, ASR does the weight re-initialization by the adaptive intervals. The adaptive interval is determined based on the change in label flipping. Our method is validated on extensive CTTA benchmarks, achieving excellent performance.

📄 PDF Abstract BibTeX arXiv:2412.20034

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationTest-time Adaptation

Similar Papers 제목 키워드 기반

Theories of synaptic memory consolidation and intelligent plasticity for continual learning

2024-05-27 · Friedemann Zenke, Axel Laborieux

Humans and animals learn throughout life. Such continual learning is crucial for intelligence. In this chapter, we examine the pivotal role plasticity mechanisms with complex internal synaptic dynamics could play in enab…

Continual Learning

Intrinsic preservation of plasticity in continual quantum learning

2025-11-21 · Yu-Qin Chen, Shi-Xin Zhang arxiv

Artificial intelligence in dynamic, real-world environments requires the capacity for continual learning. However, standard deep learning suffers from a fundamental issue: loss of plasticity, in which networks gradually …

Reinforcement LearningContinual Learning

Local Timescale Gates for Timescale-Robust Continual Spiking Neural Networks

2025-10-13 · Ansh Tiwari, Ayush Chauhan arxiv

Spiking neural networks (SNNs) promise energy-efficient artificial intelligence on neuromorphic hardware but struggle with tasks requiring both fast adaptation and long-term memory, especially in continual learning. We p…

Continual Learning

Balancing Plasticity and Stability with Fast and Slow Successor Features

2026-05-25 · Raymond Chua, Doina Precup, Blake Richards arxiv

A hallmark of intelligence is the ability to adapt in non-stationary environments, yet deep Reinforcement Learning (RL) agents often struggle in such settings. Prior studies introduce non-stationarity through abrupt shif…

Reinforcement LearningContinual Learning

Prototype-Aligned Federated Soft-Prompts for Continual Web Personalization

2026-03-29 · Canran Xiao, Liwei Hou arxiv

Continual web personalization is essential for engagement, yet real-world non-stationarity and privacy constraints make it hard to adapt quickly without forgetting long-term preferences. We target this gap by seeking a p…