ABSTRACT
The photo reflective sensor (PRS), a tiny distant-measurement module, is a popular electronic component widely used in wearable user-interfaces. An unavoidable issue of such wearable PRS devices in practical use is the need of user-independent training to have high gesture recognition accuracy. Each new user has to re-train a device by providing new training data (we call the inter-user setup). Even worse, re-training is also necessary ideally every time when the same user re-wears the device (we call the intra-user setup). In this paper, we propose a domain adaptation framework to reduce this training cost of users. Specifically, we adapt a pre-trained convolutional neural network (CNN) for both inter-user and intra-user setups to maintain the recognition accuracy high. We demonstrate, with an actual PRS device, that our framework significantly improves the average classification accuracy of the intra-user and inter-user setups up to 87.43% and 80.06% against the baseline (non-adapted) setups with the accuracy 68.96% and 63.26% respectively.
Supplemental Material
Available for Download
Supplemental material.
- John Blitzer, Ryan McDonald, and Fernando Pereira. 2006. Domain Adaptation with Structural Correspondence Learning. In EMNLP. Google ScholarDigital Library
- Jeff Donahue et al. 2013. DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. (2013).Google Scholar
- Takashi Kikuchi et al. 2017. EarTouch: Turning the Ear into an Input Surface. In MobileHCI. Google ScholarDigital Library
- Yann LeCun et al. 1989. Backpropagation applied to handwritten zip code recognition. Neural Computation 1, 4 (1989), 541--551. Google ScholarDigital Library
- Katsutoshi Masai et al. Facial Expression Recognition in Daily Life by Embedded Photo Reflective Sensors on Smart Eyewear. In IUI. Google ScholarDigital Library
- Quinn McNemar. 1947. Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika 12, 2 (01 Jun 1947), 153--157.Google Scholar
- Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs/1409.1556 (2014).Google Scholar
- Hidekazu Tanaka et al. 2011. Chewing Jockey: Augmented Food Texture by Using Sound Based on the Cross-modal Effect. In SIGGRAPH Asia 2011 Emerging Technologies (SA '11). Article 18, 1 pages. Google ScholarDigital Library
- Anusha Withana et al. 2015. zSense: Enabling Shallow Depth Gesture Recognition for Greater Input Expressivity on Smart Wearables. In CHI. Google ScholarDigital Library
- Koki Yamashita and et al. 2017. CheekInput: Turning Your Cheek into an Input Surface by Embedded Optical Sensors on a Head-mounted Display. In ACM VRST. ACM, 19:1--19:8. Google ScholarDigital Library
Recommendations
Semi-supervised adversarial discriminative domain adaptation
AbstractDomain adaptation is a potential method to train a powerful deep neural network across various datasets. More precisely, domain adaptation methods train the model on training data and test that model on a completely separate dataset. The ...
Cross-user gesture recognition from sEMG signals using an optimal transport assisted student-teacher framework
AbstractThe cross-user gesture recognition is a puzzle in the myoelectric control system, owing to great variability in muscle activities across different users. To address this problem, a novel optimal transport (OT) assisted student-teacher (ST) ...
Highlights- A novel framework is proposed for cross-user myoelectric pattern-recognition control.
- The proposed framework relies on a student-teacher model assisted with optimal transport.
- The proposed framework allows the classifier to be ...
Distributionally robust unsupervised domain adaptation
AbstractObtaining ground-truth label information from real-world data along with uncertainty quantification can be difficult or even infeasible. In the absence of labeled data for a certain task, unsupervised domain adaptation (UDA) techniques ...
Comments