EarDA: Towards Accurate and Data-Efficient Earable Activity Sensing

In the realm of smart sensing with the Internet of Things, earable devices are empowered with the capability of multi-modality sensing and intelligence of context-aware computing, leading to its wide usage in Human Activity Recognition (HAR). Nonetheless, unlike the movements captured by Inertial Measurement Unit (IMU) sensors placed on the upper or lower body, those motion signals obtained from earable devices show significant changes in amplitudes and patterns, especially in the presence of dynamic and unpredictable head movements, posing a significant challenge for activity classification. In this work, we present EarDA, an adversarial-based domain adaptation system to extract the domain-independent features across different sensor locations. Moreover, while most deep learning methods commonly rely on training with substantial amounts of labeled data to offer good accuracy, the proposed scheme can release the potential usage of publicly available smartphone-based IMU datasets. Furthermore, we explore the feasibility of applying a filter-based data processing method to mitigate the impact of head movement. EarDA, the proposed system, enables more data-efficient and accurate activity sensing. It achieves an accuracy of 88.8% under HAR task, demonstrating a significant 43% improvement over methods without domain adaptation. This clearly showcases its effectiveness in mitigating domain gaps.

Learning Orientation-Estimation Convolutional Neural Network for Building Detection in Optical Remote Sensing Image

Benefiting from the great success of deep learning in computer vision, CNN-based object detection methods have drawn significant attentions. Various frameworks have been proposed which show awesome and robust performance for a large range of datasets. However, for building detection in remote sensing images, buildings always pose a diversity of orientations which makes it a challenge for the application of off-the-shelf methods to building detection. In this work, we aim to integrate orientation regression into the popular axis-aligned bounding-box detection method to tackle this problem. To adapt the axis-aligned bounding boxes to arbitrarily orientated ones, we also develop an algorithm to estimate the Intersection over Union (IoU) overlap between any two arbitrarily oriented boxes which is convenient to implement in Graphics Processing Unit (GPU) for accelerating computation. The proposed method utilizes CNN for both robust feature extraction and rotated bounding box regression. We present our modelin an end-to-end fashion making it easy to train. The model is formulated and trained to predict orientation, location and extent simultaneously obtaining tighter bounding box and hence, higher mean average precision (mAP). Experiments on remote sensing images of different scales shows a promising performance over the conventional one.

A Labeling-Free Approach to Supervising Deep Neural Networks for Retinal Blood Vessel Segmentation

Segmenting blood vessels in fundus imaging plays an important role in medical diagnosis. Many algorithms have been proposed. While deep Neural Networks have been attracting enormous attention from computer vision community recent years and several novel works have been done in terms of its application in retinal blood vessel segmentation, most of them are based on supervised learning which requires amount of labeled data, which is both scarce and expensive to obtain. We leverage the power of Deep Convolutional Neural Networks (DCNN) in feature learning, in this work, to achieve this ultimate goal. The highly efficient feature learning of DCNN inspires our novel approach that trains the networks with automatically-generated samples to achieve desirable performance on real-world fundus images. For this, we design a set of rules abstracted from the domain-specific prior knowledge to generate these samples. We argue that, with the high efficiency of DCNN in feature learning, one can achieve this goal by constructing the training dataset with prior knowledge, no manual labeling is needed. This approach allows us to take advantages of supervised learning without labeling. We also build a naive DCNN model to test it. The results on standard benchmarks of fundus imaging show it is competitive to the state-of-the-art methods which implies a potential way to leverage the power of DCNN in feature learning.