# Low-Cost On-device Partial Domain Adaptation (LoCO-PDA): Enabling efficient CNN retraining on edge devices

arXiv: https://arxiv.org/abs/2203.00772 · HTML: https://mlsanity.com/paper/2203.00772/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 1 Mar 2022.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Partial Adversarial Domain Adaptation](https://mlsanity.com/paper/1808.04205/) (2018)
- [Importance Weighted Adversarial Nets for Partial Domain Adaptation](https://mlsanity.com/paper/1803.09210/) (2018)
- [Learning to Transfer Examples for Partial Domain Adaptation](https://mlsanity.com/paper/1903.12230/) (2019)
- [It's always personal: Using Early Exits for Efficient On-Device CNN Personalisation](https://mlsanity.com/paper/2102.01393/) (2021)
- [Now that I can see, I can improve: Enabling data-driven finetuning of CNNs on the edge](https://mlsanity.com/paper/2006.08554/) (2020)
- [perf4sight: A toolflow to model CNN training performance on Edge GPUs](https://mlsanity.com/paper/2108.05580/) (2021)

## Abstract (arXiv)

With the increased deployment of Convolutional Neural Networks (CNNs) on edge devices, the uncertainty of the observed data distribution upon deployment has led researchers to to utilise large and extensive datasets such as ILSVRC'12 to train CNNs. Consequently, it is likely that the observed data distribution upon deployment is a subset of the training data distribution. In such cases, not adapting a network to the observed data distribution can cause performance degradation due to negative transfer and alleviating this is the focus of Partial Domain Adaptation (PDA). Current works targeting PDA do not focus on performing the domain adaptation on an edge device, adapting to a changing target distribution or reducing the cost of deploying the adapted network. This work proposes a novel PDA methodology that targets all of these directions and opens avenues for on-device PDA. LoCO-PDA adapts a deployed network to the observed data distribution by enabling it to be retrained on an edge device. Across subsets of the ILSVRC12 dataset, LoCO-PDA improves classification accuracy by 3.04pp on average while achieving up to 15.1x reduction in retraining memory consumption and 2.07x improvement in inference latency on the NVIDIA Jetson TX2. The work is open-sourced at link removed for anonymity.