论文标题
低成本的evice部分域适应（Loco-PDA）：在边缘设备上启用有效的CNN再培训
Low-Cost On-device Partial Domain Adaptation (LoCO-PDA): Enabling efficient CNN retraining on edge devices
论文作者
论文摘要
随着边缘设备上卷积神经网络（CNN）的部署增加，部署时观察到的数据分布的不确定性使研究人员能够利用大型且广泛的数据集（例如ILSVRC'12）来培训CNN。因此，部署时观察到的数据分布可能是培训数据分布的一部分。在这种情况下，不将网络适应观察到的数据分布会导致由于负转移而导致性能降解，并且减轻了这是部分域适应（PDA）的重点。针对PDA的当前作品并不专注于在边缘设备上执行域的适应性，适应不断变化的目标分布或降低部署适应网络的成本。这项工作提出了一种新颖的PDA方法，该方法针对所有这些方向并为eve依的PDA开放了途径。 Loco-PDA通过在边缘设备上启用重新训练来调整已部署的网络对观察到的数据分布。在ILSVRC12数据集的子集中，Loco-PDA平均提高了3.04pp的分类准确性，同时可减少15.1倍的降低重新培训记忆消耗，并提高NVIDIA JETSON JETSON TX2的推断潜伏期2.07倍。该作品的开源为\ emph {link for Anonymity}。
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}.
