Specifically, we describe adaptations for scenarios with 2D and 3D inputs, uni and multi-label classification, and class distribution mismatch between labeled and unlabeled portions of the training data.
Our results strongly argue for the use of superpixel-based AL for semantic segmentation and highlight the importance of using realistic annotation costs in evaluating such methods.
Deep learning models are the state-of-the-art methods for semantic point cloud segmentation, the success of which relies on the availability of large-scale annotated datasets.
Despite the vast literature on Human Activity Recognition (HAR) with wearable inertial sensor data, it is perhaps surprising that there are few studies investigating semisupervised learning for HAR, particularly in a challenging scenario with class imbalance problem.
To this end, we introduce TEA-DNN, a NAS algorithm targeting multi-objective optimization of execution time, energy consumption, and classification accuracy of CNN workloads on embedded architectures.