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

arXiv: https://arxiv.org/abs/2106.07268 · HTML: https://mlsanity.com/paper/2106.07268/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 14 Jun 2021.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [Progress & Compress: A scalable framework for continual learning](https://mlsanity.com/paper/1805.06370/) (2018)
- [Measuring Catastrophic Forgetting in Neural Networks](https://mlsanity.com/paper/1708.02072/) (2017)
- [Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1](https://mlsanity.com/paper/1602.02830/) (2016)
- [MNN: A Universal and Efficient Inference Engine](https://mlsanity.com/paper/2002.12418/) (2020)
- [A comprehensive, application-oriented study of catastrophic forgetting in DNNs](https://mlsanity.com/paper/1905.08101/) (2019)
- [On-Device Neural Net Inference with Mobile GPUs](https://mlsanity.com/paper/1907.01989/) (2019)
- [DSP.Ear: Leveraging Co-Processor Support for Continuous Audio Sensing on Smartphones](https://mlsanity.com/paper/1409.3206/) (2014)
- [Knowing when we do not know: Bayesian continual learning for sensing-based analysis tasks](https://mlsanity.com/paper/2106.05872/) (2021)

## Built on by (most cited first, 9 of 9)

- [Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications](https://mlsanity.com/paper/2110.13290/) (2021)
- [LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms](https://mlsanity.com/paper/2311.11420/) (2023)
- [Enabling On-Device Smartphone GPU based Training: Lessons Learned](https://mlsanity.com/paper/2202.10100/) (2022)
- [YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers](https://mlsanity.com/paper/2203.03794/) (2022)
- [Learning New Concepts, Remembering the Old: Continual Learning for Multimodal Concept Bottleneck Models](https://mlsanity.com/paper/2411.17471/) (2024)
- [Characterizing Continual Learning Scenarios and Strategies for Audio Analysis](https://mlsanity.com/paper/2407.00465/) (2024)
- [TS-ACL: Closed-Form Solution for Time Series-oriented Continual Learning](https://mlsanity.com/paper/2410.15954/) (2024)
- [Improving Feature Generalizability with Multitask Learning in Class Incremental Learning](https://mlsanity.com/paper/2204.12915/) (2022)
- [MetaCLBench: Meta Continual Learning Benchmark on Resource-Constrained Edge Devices](https://mlsanity.com/paper/2504.00174/) (2025)

## Abstract (arXiv)

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% and the storage requirements by 2-4 times without sacrificing its performance. FastICARL enables complete on-device IL, ensuring user privacy as the user data does not need to leave the device.