AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments
Guardat en:
| Publicat a: | arXiv.org (Oct 10, 2024), p. n/a |
|---|---|
| Autor principal: | |
| Altres autors: | , , , , , |
| Publicat: |
Cornell University Library, arXiv.org
|
| Matèries: | |
| Accés en línia: | Citation/Abstract Full text outside of ProQuest |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3116452596 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2331-8422 | ||
| 024 | 7 | |a 10.1145/3666025.3699339 |2 doi | |
| 035 | |a 3116452596 | ||
| 045 | 0 | |b d20241010 | |
| 100 | 1 | |a Cheng, Fang | |
| 245 | 1 | |a AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments | |
| 260 | |b Cornell University Library, arXiv.org |c Oct 10, 2024 | ||
| 513 | |a Working Paper | ||
| 520 | 3 | |a On-device adapting to continual, unpredictable domain shifts is essential for mobile applications like autonomous driving and augmented reality to deliver seamless user experiences in evolving environments. Test-time adaptation (TTA) emerges as a promising solution by tuning model parameters with unlabeled live data immediately before prediction. However, TTA's unique forward-backward-reforward pipeline notably increases the latency over standard inference, undermining the responsiveness in time-sensitive mobile applications. This paper presents AdaShadow, a responsive test-time adaptation framework for non-stationary mobile data distribution and resource dynamics via selective updates of adaptation-critical layers. Although the tactic is recognized in generic on-device training, TTA's unsupervised and online context presents unique challenges in estimating layer importance and latency, as well as scheduling the optimal layer update plan. AdaShadow addresses these challenges with a backpropagation-free assessor to rapidly identify critical layers, a unit-based runtime predictor to account for resource dynamics in latency estimation, and an online scheduler for prompt layer update planning. Also, AdaShadow incorporates a memory I/O-aware computation reuse scheme to further reduce latency in the reforward pass. Results show that AdaShadow achieves the best accuracy-latency balance under continual shifts. At low memory and energy costs, Adashadow provides a 2x to 3.5x speedup (ms-level) over state-of-the-art TTA methods with comparable accuracy and a 14.8% to 25.4% accuracy boost over efficient supervised methods with similar latency. | |
| 653 | |a Accuracy | ||
| 653 | |a Augmented reality | ||
| 653 | |a Testing time | ||
| 653 | |a Applications programs | ||
| 653 | |a Energy costs | ||
| 653 | |a Parameter sensitivity | ||
| 653 | |a Mobile computing | ||
| 653 | |a Adaptation | ||
| 653 | |a Resource scheduling | ||
| 653 | |a User experience | ||
| 653 | |a Computer aided scheduling | ||
| 653 | |a Estimation | ||
| 653 | |a Back propagation | ||
| 653 | |a Uniqueness | ||
| 653 | |a Run time (computers) | ||
| 700 | 1 | |a Liu, Sicong | |
| 700 | 1 | |a Zhou, Zimu | |
| 700 | 1 | |a Guo, Bin | |
| 700 | 1 | |a Tang, Jiaqi | |
| 700 | 1 | |a Ma, Ke | |
| 700 | 1 | |a Yu, Zhiwen | |
| 773 | 0 | |t arXiv.org |g (Oct 10, 2024), p. n/a | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3116452596/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |
| 856 | 4 | 0 | |3 Full text outside of ProQuest |u http://arxiv.org/abs/2410.08256 |