Maintain Plasticity in Long-timescale Continual Test-time Adaptation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationTest-time AdaptationSimilar Papers 제목 키워드 기반
Theories of synaptic memory consolidation and intelligent plasticity for continual learning
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 LearningIntrinsic preservation of plasticity in continual quantum learning
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 LearningLocal Timescale Gates for Timescale-Robust Continual Spiking Neural Networks
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 LearningBalancing Plasticity and Stability with Fast and Slow Successor Features
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 LearningPrototype-Aligned Federated Soft-Prompts for Continual Web Personalization
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…