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

arXiv: https://arxiv.org/abs/2503.15889 · HTML: https://mlsanity.com/paper/2503.15889/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [Robust Test-Time Adaptation in Dynamic Scenarios](https://mlsanity.com/paper/2303.13899/) (2023)
- [Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection](https://mlsanity.com/paper/2101.03778/) (2021)
- [On Pitfalls of Test-Time Adaptation](https://mlsanity.com/paper/2306.03536/) (2023)
- [On-Device Machine Learning: An Algorithms and Learning Theory Perspective](https://mlsanity.com/paper/1911.00623/) (2019)
- [SITA: Single Image Test-time Adaptation](https://mlsanity.com/paper/2112.02355/) (2021)
- [Revisiting Batch Normalization for Improving Corruption Robustness](https://mlsanity.com/paper/2010.03630/) (2020)
- [Automatic acoustic detection of birds through deep learning: the first Bird Audio Detection challenge](https://mlsanity.com/paper/1807.05812/) (2018)
- [Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading](https://mlsanity.com/paper/2206.07509/) (2022)
- [Sounds of COVID-19: exploring realistic performance of audio-based digital testing](https://mlsanity.com/paper/2106.15523/) (2021)
- [TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge](https://mlsanity.com/paper/2307.09988/) (2023)
- [Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamics](https://mlsanity.com/paper/2104.11849/) (2021)
- [ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection](https://mlsanity.com/paper/2312.14227/) (2023)
- [Unraveling Batch Normalization for Realistic Test-Time Adaptation](https://mlsanity.com/paper/2312.09486/) (2023)
- [Medical Image Segmentation with InTEnt: Integrated Entropy Weighting for Single Image Test-Time Adaptation](https://mlsanity.com/paper/2402.09604/) (2024)
- [On-Device Domain Generalization](https://mlsanity.com/paper/2209.07521/) (2022)

## Built on by (most cited first, 1 of 1)

- [FORGE: Forward-Only Test-Time Adaptation for Integer-Only Vision Models on Microcontrollers](https://mlsanity.com/paper/2609.01683/) (2026)

## Abstract (arXiv)

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.