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

TL;DR

This paper introduces LoCO-PDA, a low-cost method for on-device partial domain adaptation of CNNs, enabling efficient retraining on edge devices to improve accuracy and reduce resource consumption.

Contribution

It presents a novel PDA approach that allows CNNs to be adapted directly on edge devices, addressing cost, efficiency, and dynamic target distribution challenges.

Findings

Improves classification accuracy by 3.04 percentage points on average.

Achieves up to 15.1x reduction in retraining memory consumption.

Provides 2.07x faster inference latency on NVIDIA Jetson TX2.

Abstract

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 \emph{link removed for anonymity}.