Search for: All records

Augmented Reality (AR) enables elements of a computer-generated digital world to be integrated with a user’s perception of the physical world. Smart glasses, like smart phones, have independent operating systems and they can support a variety of different applications and modes of communication to support augmented reality. This paper details the development of a novel new application that extends a widely-used mobile app for phenotyping and allows agronomists to interact with the app while keeping their hands free to perform field work. The smart glasses accept voice commands from the user and communicate with the mobile phone app via Bluetooth. In addition, changes detected by the mobile phone are displayed to the user on the smart glasses. This enables agronomists to efficiently collect phenotypic data. 

Linear encoding of sparse vectors is widely popular, but is commonly data-independent – missing any possible extra (but a priori unknown) structure beyond sparsity. In this paper we present a new method to learn linear encoders that adapt to data, while still performing well with the widely used l1 decoder. The convex l1 decoder prevents gradient propagation as needed in standard gradient-based training. Our method is based on the insight that unrolling the convex decoder into T projected subgradient steps can address this issue. Our method can be seen as a data-driven way to learn a compressed sensing measurement matrix. We compare the empirical performance of 10 algorithms over 6 sparse datasets (3 synthetic and 3 real). Our experiments show that there is indeed additional structure beyond sparsity in the real datasets; our method is able to discover it and exploit it to create excellent reconstructions with fewer measurements (by a factor of 1.1-3x) compared to the previous state-of-the-art methods. We illustrate an application of our method in learning label embeddings for extreme multi-label classification, and empirically show that our method is able to match or outperform the precision scores of SLEEC, which is one of the state-of-the-art embedding-based approaches.