Pavan Turaga
Arizona State University
Publications 8
Exploiting known semantic relationships between fine-grained tasks is critical to the success of recent model agnostic approaches. These approaches often rely on meta-optimization to make a model robust to systematic task or domain shifts. However, in practice, the performance of these methods can suffer, when there are no coherent semantic relationships between the tasks (or domains). We present Invenio, a structured meta-learning algorithm to infer semantic similarities between a given set of ...
Sep 1, 2019 in ICIP (International Conference on Image Processing)
#1Juan Andrade (ASU: Arizona State University)H-Index: 1
#2Pavan Turaga (ASU: Arizona State University)H-Index: 2
Last.Andreas Spanias (ASU: Arizona State University)H-Index: 28
view all 3 authors...
Last.Farib KhondokerH-Index: 1
view all 13 authors...
Topological features such as persistence diagrams and their functional approximations like persistence images (PIs) have been showing substantial promise for machine learning and computer vision applications. Key bottlenecks to their large scale adoption are computational expenditure and difficulty in incorporating them in a differentiable architecture. We take an important step in this paper to mitigate these bottlenecks by proposing a novel one-step approach to generate PIs directly from the i...
#1Eduardo Salazar (UCSF: University of California, San Francisco)
#2Mayank Gupta (ASU: Arizona State University)H-Index: 1
Last.Matthew P. Buman (UCSF: University of California, San Francisco)
view all 7 authors...
Obstructive sleep apnea (OSA) is an under-diagnosed risk factor for several adverse health outcomes. The gold standard diagnostic test for OSA is laboratory-based polysomnography (PSG). Portable sl...
#1Suhas Lohit (ASU: Arizona State University)H-Index: 6
#2Kuldeep Kulkarni (ASU: Arizona State University)H-Index: 7
Last.Amit Ashok (UA: University of Arizona)H-Index: 13
view all 5 authors...
Traditional algorithms for compressive sensing recovery are computationally expensive and are ineffective at low measurement rates. In this paper, we propose a data-driven noniterative algorithm to overcome the shortcomings of earlier iterative algorithms. Our solution, ReconNet , is a deep neural network, which is learned end-to-end to map block-wise compressive measurements of the scene to the desired image blocks. Reconstruction of an image becomes a simple forward pass through the network an...
13 CitationsSource
#1Sameeksha Katoch (ASU: Arizona State University)H-Index: 3
#2Gowtham Muniraju (ASU: Arizona State University)H-Index: 3
Last.Devarajan SrinivasanH-Index: 5
view all 8 authors...
This paper describes three methods used in the development of a utility-scale solar cyber-physical system. The study describes remote fault detection using machine learning approaches, power output optimization using cloud movement prediction and consensus-based solar array parameter estimation. Dynamic cloud movement, shading and soiling, lead to fluctuations in power output and loss of efficiency. For optimization of output power, a cloud movement prediction algorithm is proposed. Integrated f...
7 CitationsSource
In resource-constrained environments, one can employ spatial multiplexing cameras to acquire a small number of measurements of a scene, and perform effective reconstruction or high-level inference using purely data-driven neural networks. However, once trained, the measurement matrix and the network are valid only for a single measurement rate (MR) chosen at training time. To overcome this drawback, we answer the following question: How can we jointly design the measurement operator and the reco...
2 Citations