LeanTTA: A Backpropagation-Free and Stateless Approach to Quantized Test-Time Adaptation on Edge Devices

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dong, Cynthia, Jia, Hong, Kwon, Young D., Rizos, Georgios, Mascolo, Cecilia
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910886018416640
author Dong, Cynthia
Jia, Hong
Kwon, Young D.
Rizos, Georgios
Mascolo, Cecilia
author_facet Dong, Cynthia
Jia, Hong
Kwon, Young D.
Rizos, Georgios
Mascolo, Cecilia
contents While there are many advantages to deploying machine learning models on edge devices, the resource constraints of mobile platforms, the dynamic nature of the environment, and differences between the distribution of training versus in-the-wild data make such deployments challenging. Current test-time adaptation methods are often memory-intensive and not designed to be quantization-compatible or deployed on low-resource devices. To address these challenges, we present LeanTTA, a novel backpropagation-free and stateless framework for quantized test-time adaptation tailored to edge devices. Our approach minimizes computational costs by dynamically updating normalization statistics without backpropagation, which frees LeanTTA from the common pitfall of relying on large batches and historical data, making our method robust to realistic deployment scenarios. Our approach is the first to enable further computational gains by combining partial adaptation with quantized module fusion. We validate our framework across sensor modalities, demonstrating significant improvements over state-of-the-art TTA methods, including a 15.7% error reduction, peak memory usage of only 11.2MB for ResNet18, and fast adaptation within an order-of-magnitude of normal inference speeds on-device. LeanTTA provides a robust solution for achieving the right trade offs between accuracy and system efficiency in edge deployments, addressing the unique challenges posed by limited data and varied operational conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2503_15889
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LeanTTA: A Backpropagation-Free and Stateless Approach to Quantized Test-Time Adaptation on Edge Devices
Dong, Cynthia
Jia, Hong
Kwon, Young D.
Rizos, Georgios
Mascolo, Cecilia
Machine Learning
Artificial Intelligence
While there are many advantages to deploying machine learning models on edge devices, the resource constraints of mobile platforms, the dynamic nature of the environment, and differences between the distribution of training versus in-the-wild data make such deployments challenging. Current test-time adaptation methods are often memory-intensive and not designed to be quantization-compatible or deployed on low-resource devices. To address these challenges, we present LeanTTA, a novel backpropagation-free and stateless framework for quantized test-time adaptation tailored to edge devices. Our approach minimizes computational costs by dynamically updating normalization statistics without backpropagation, which frees LeanTTA from the common pitfall of relying on large batches and historical data, making our method robust to realistic deployment scenarios. Our approach is the first to enable further computational gains by combining partial adaptation with quantized module fusion. We validate our framework across sensor modalities, demonstrating significant improvements over state-of-the-art TTA methods, including a 15.7% error reduction, peak memory usage of only 11.2MB for ResNet18, and fast adaptation within an order-of-magnitude of normal inference speeds on-device. LeanTTA provides a robust solution for achieving the right trade offs between accuracy and system efficiency in edge deployments, addressing the unique challenges posed by limited data and varied operational conditions.
title LeanTTA: A Backpropagation-Free and Stateless Approach to Quantized Test-Time Adaptation on Edge Devices
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2503.15889