Low-Cost On-device Partial Domain Adaptation (LoCO-PDA) : Enabling Efficient CNN Retraining on Edge Devices

Add to your list(s) Download to your calendar using vCal

• Aditya Rajagopal
• Monday 18 October 2021, 16:00-17:00
• Teams (in the "CAS Seminars" team).

If you have a question about this talk, please contact George A Constantinides.

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 the field of Partial Domain Adaptation (PDA). However, the majority of current works targeting PDA do not focus on performing the domain adapation 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 constraints and opens avenues for near-real-time on-device PDA . By reducing the cost of retraining a CNN , LoCO-PDA enables a pruned network to be retrained on an edge device allowing it to adapt to changes in the observed data distribution. 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 .

This talk is part of the CAS Talks series.

This talk is included in these lists:

• Andrea Picciau's list
• CAS Talks
• Circuits and Systems Group: Internal Seminars
• Teams (in the "CAS Seminars" team)

Note that ex-directory lists are not shown.