Header

UZH-Logo

Maintenance Infos

Fast event-driven incremental learning of hand symbols


Lungu, Iulia Alexandra; Liu, Shih-Chii; Delbruck, Tobi (2019). Fast event-driven incremental learning of hand symbols. In: 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), Hsinchu, Taiwan, 18 March 2019 - 20 March 2019.

Abstract

This paper describes a hand symbol recognition system that can quickly be trained to incrementally learn to recognize new symbols using about 100 times less data and time than by using conventional training. It is driven by frames from a Dynamic Vision Sensor (DVS) event camera. Conventional cameras have very redundant output, especially at high frame rates. Dynamic vision sensors output sparse and asynchronous brightness change events that occur when an object or the camera is moving. Images consisting of a fixed number of events from a DVS drive recognition and incremental learning of new hand symbols in the context of a RoShamBo (rock-paper-scissors) demonstration. Conventional training on the original RoShamBo dataset requires about 12.5h compute time on a desktop GPU using the 2.5 million images in the base dataset. Novel symbols that a user shows for a few tens of seconds to the system can be learned on-the-fly using the iCaRL incremental learning algorithm with 3 minutes of training time on a desktop GPU, while preserving recognition accuracy of previously trained symbols. Our system runs a residual network with 32 layers and maintains 88.4% after 100 epochs or 77% after 5 epochs overall accuracy after 4 incremental training stages. Each stage adds an additional 2 novel symbols to the base 4 symbols. The paper also reports an inexpensive robot hand used for live demonstrations of the base RoShamBo game.

Abstract

This paper describes a hand symbol recognition system that can quickly be trained to incrementally learn to recognize new symbols using about 100 times less data and time than by using conventional training. It is driven by frames from a Dynamic Vision Sensor (DVS) event camera. Conventional cameras have very redundant output, especially at high frame rates. Dynamic vision sensors output sparse and asynchronous brightness change events that occur when an object or the camera is moving. Images consisting of a fixed number of events from a DVS drive recognition and incremental learning of new hand symbols in the context of a RoShamBo (rock-paper-scissors) demonstration. Conventional training on the original RoShamBo dataset requires about 12.5h compute time on a desktop GPU using the 2.5 million images in the base dataset. Novel symbols that a user shows for a few tens of seconds to the system can be learned on-the-fly using the iCaRL incremental learning algorithm with 3 minutes of training time on a desktop GPU, while preserving recognition accuracy of previously trained symbols. Our system runs a residual network with 32 layers and maintains 88.4% after 100 epochs or 77% after 5 epochs overall accuracy after 4 incremental training stages. Each stage adds an additional 2 novel symbols to the base 4 symbols. The paper also reports an inexpensive robot hand used for live demonstrations of the base RoShamBo game.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

0 downloads since deposited on 11 Feb 2020
0 downloads since 12 months

Additional indexing

Item Type:Conference or Workshop Item (Paper), not_refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Event End Date:20 March 2019
Deposited On:11 Feb 2020 13:39
Last Modified:16 Feb 2020 07:08
Publisher:IEEE
ISBN:9781538678848
OA Status:Closed
Publisher DOI:https://doi.org/10.1109/aicas.2019.8771472

Download

Closed Access: Download allowed only for UZH members