Training Deep Neural Networks for Wireless Sensor Networks Using Loosely and Weakly Labeled Images
This work addresses the problem of efficient image recognition in resource-limited WSNs, representing an incremental improvement with domain-specific application.
The authors tackled the challenge of applying deep neural networks to Wireless Sensor Networks (WSNs) for image recognition under resource constraints by proposing a Cost-Effective Domain Generalization (CEDG) algorithm, which reduced the category-level averaged error by 41.12% on an unseen target domain and enabled real-time recognition with about 7M multiplications per prediction.
Although deep learning has achieved remarkable successes over the past years, few reports have been published about applying deep neural networks to Wireless Sensor Networks (WSNs) for image targets recognition where data, energy, computation resources are limited. In this work, a Cost-Effective Domain Generalization (CEDG) algorithm has been proposed to train an efficient network with minimum labor requirements. CEDG transfers networks from a publicly available source domain to an application-specific target domain through an automatically allocated synthetic domain. The target domain is isolated from parameters tuning and used for model selection and testing only. The target domain is significantly different from the source domain because it has new target categories and is consisted of low-quality images that are out of focus, low in resolution, low in illumination, low in photographing angle. The trained network has about 7M (ResNet-20 is about 41M) multiplications per prediction that is small enough to allow a digital signal processor chip to do real-time recognitions in our WSN. The category-level averaged error on the unseen and unbalanced target domain has been decreased by 41.12%.