# MobileTL: On-device Transfer Learning with Inverted Residual Blocks

arXiv: https://arxiv.org/abs/2212.03246 · HTML: https://mlsanity.com/paper/2212.03246/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 5 Dec 2022.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision](https://mlsanity.com/paper/1905.03696/) (2019)
- [Sparse Networks from Scratch: Faster Training without Losing Performance](https://mlsanity.com/paper/1907.04840/) (2019)
- [Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization](https://mlsanity.com/paper/1902.05967/) (2019)
- [Training and Inference with Integers in Deep Neural Networks](https://mlsanity.com/paper/1802.04680/) (2018)
- [Towards Unified INT8 Training for Convolutional Neural Network](https://mlsanity.com/paper/1912.12607/) (2019)
- [When Machine Learning Meets Privacy: A Survey and Outlook](https://mlsanity.com/paper/2011.11819/) (2020)
- [K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning](https://mlsanity.com/paper/1810.10703/) (2018)

## Built on by (most cited first, 6 of 6)

- [Training Machine Learning models at the Edge: A Survey](https://mlsanity.com/paper/2403.02619/) (2024)
- [DaCapo: Accelerating Continuous Learning in Autonomous Systems for Video Analytics](https://mlsanity.com/paper/2403.14353/) (2024)
- [Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models](https://mlsanity.com/paper/2312.14923/) (2023)
- [FedPAE: Peer-Adaptive Ensemble Learning for Asynchronous and Model-Heterogeneous Federated Learning](https://mlsanity.com/paper/2410.14075/) (2024)
- [Accelerated Training on Low-Power Edge Devices](https://mlsanity.com/paper/2502.18323/) (2025)
- [Distributed Convolutional Neural Network Training on Mobile and Edge Clusters](https://mlsanity.com/paper/2409.09083/) (2024)

## Abstract (arXiv)

Transfer learning on edge is challenging due to on-device limited resources. Existing work addresses this issue by training a subset of parameters or adding model patches. Developed with inference in mind, Inverted Residual Blocks (IRBs) split a convolutional layer into depthwise and pointwise convolutions, leading to more stacking layers, e.g., convolution, normalization, and activation layers. Though they are efficient for inference, IRBs require that additional activation maps are stored in memory for training weights for convolution layers and scales for normalization layers. As a result, their high memory cost prohibits training IRBs on resource-limited edge devices, and making them unsuitable in the context of transfer learning. To address this issue, we present MobileTL, a memory and computationally efficient on-device transfer learning method for models built with IRBs. MobileTL trains the shifts for internal normalization layers to avoid storing activation maps for the backward pass. Also, MobileTL approximates the backward computation of the activation layer (e.g., Hard-Swish and ReLU6) as a signed function which enables storing a binary mask instead of activation maps for the backward pass. MobileTL fine-tunes a few top blocks (close to output) rather than propagating the gradient through the whole network to reduce the computation cost. Our method reduces memory usage by 46% and 53% for MobileNetV2 and V3 IRBs, respectively. For MobileNetV3, we observe a 36% reduction in floating-point operations (FLOPs) when fine-tuning 5 blocks, while only incurring a 0.6% accuracy reduction on CIFAR10. Extensive experiments on multiple datasets demonstrate that our method is Pareto-optimal (best accuracy under given hardware constraints) compared to prior work in transfer learning for edge devices.