DeepAI AI Chat
Log In Sign Up

FastICARL: Fast Incremental Classifier and Representation Learning with Efficient Budget Allocation in Audio Sensing Applications

by   Young D. Kwon, et al.

Various incremental learning (IL) approaches have been proposed to help deep learning models learn new tasks/classes continuously without forgetting what was learned previously (i.e., avoid catastrophic forgetting). With the growing number of deployed audio sensing applications that need to dynamically incorporate new tasks and changing input distribution from users, the ability of IL on-device becomes essential for both efficiency and user privacy. However, prior works suffer from high computational costs and storage demands which hinders the deployment of IL on-device. In this work, to overcome these limitations, we develop an end-to-end and on-device IL framework, FastICARL, that incorporates an exemplar-based IL and quantization in the context of audio-based applications. We first employ k-nearest-neighbor to reduce the latency of IL. Then, we jointly utilize a quantization technique to decrease the storage requirements of IL. We implement FastICARL on two types of mobile devices and demonstrate that FastICARL remarkably decreases the IL time up to 78-92 performance. FastICARL enables complete on-device IL, ensuring user privacy as the user data does not need to leave the device.


page 1

page 2

page 3

page 4


Two-Level Residual Distillation based Triple Network for Incremental Object Detection

Modern object detection methods based on convolutional neural network su...

ZKSENSE: a Privacy-Preserving Mechanism for Bot Detection in Mobile Devices

CAPTCHA systems have been widely deployed to identify and block fraudule...

Accelerating Deep Learning Model Inference on Arm CPUs with Ultra-Low Bit Quantization and Runtime

Deep Learning has been one of the most disruptive technological advancem...

Do Not Forget to Attend to Uncertainty while Mitigating Catastrophic Forgetting

One of the major limitations of deep learning models is that they face c...

Confidential Deep Learning: Executing Proprietary Models on Untrusted Devices

Performing deep learning on end-user devices provides fast offline infer...

Incremental Learning via Rate Reduction

Current deep learning architectures suffer from catastrophic forgetting,...

AppStreamer: Reducing Storage Requirements of Mobile Games through Predictive Streaming

Storage has become a constrained resource on smartphones. Gaming is a po...