Matching Items (57)
Filtering by
- All Subjects: Computer Science
- All Subjects: Image processing--Digital techniques.
- Creators: Turaga, Pavan
Description
Deep neural networks (DNNs) have had tremendous success in a variety of
statistical learning applications due to their vast expressive power. Most
applications run DNNs on the cloud on parallelized architectures. There is a need
for for efficient DNN inference on edge with low precision hardware and analog
accelerators. To make trained models more robust for this setting, quantization and
analog compute noise are modeled as weight space perturbations to DNNs and an
information theoretic regularization scheme is used to penalize the KL-divergence
between perturbed and unperturbed models. This regularizer has similarities to
both natural gradient descent and knowledge distillation, but has the advantage of
explicitly promoting the network to and a broader minimum that is robust to
weight space perturbations. In addition to the proposed regularization,
KL-divergence is directly minimized using knowledge distillation. Initial validation
on FashionMNIST and CIFAR10 shows that the information theoretic regularizer
and knowledge distillation outperform existing quantization schemes based on the
straight through estimator or L2 constrained quantization.
statistical learning applications due to their vast expressive power. Most
applications run DNNs on the cloud on parallelized architectures. There is a need
for for efficient DNN inference on edge with low precision hardware and analog
accelerators. To make trained models more robust for this setting, quantization and
analog compute noise are modeled as weight space perturbations to DNNs and an
information theoretic regularization scheme is used to penalize the KL-divergence
between perturbed and unperturbed models. This regularizer has similarities to
both natural gradient descent and knowledge distillation, but has the advantage of
explicitly promoting the network to and a broader minimum that is robust to
weight space perturbations. In addition to the proposed regularization,
KL-divergence is directly minimized using knowledge distillation. Initial validation
on FashionMNIST and CIFAR10 shows that the information theoretic regularizer
and knowledge distillation outperform existing quantization schemes based on the
straight through estimator or L2 constrained quantization.
ContributorsKadambi, Pradyumna (Author) / Berisha, Visar (Thesis advisor) / Dasarathy, Gautam (Committee member) / Seo, Jae-Sun (Committee member) / Cao, Yu (Committee member) / Arizona State University (Publisher)
Created2019
Description
Over the last decade, deep neural networks also known as deep learning, combined with large databases and specialized hardware for computation, have made major strides in important areas such as computer vision, computational imaging and natural language processing. However, such frameworks currently suffer from some drawbacks. For example, it is generally not clear how the architectures are to be designed for different applications, or how the neural networks behave under different input perturbations and it is not easy to make the internal representations and parameters more interpretable. In this dissertation, I propose building constraints into feature maps, parameters and and design of algorithms involving neural networks for applications in low-level vision problems such as compressive imaging and multi-spectral image fusion, and high-level inference problems including activity and face recognition. Depending on the application, such constraints can be used to design architectures which are invariant/robust to certain nuisance factors, more efficient and, in some cases, more interpretable. Through extensive experiments on real-world datasets, I demonstrate these advantages of the proposed methods over conventional frameworks.
ContributorsLohit, Suhas Anand (Author) / Turaga, Pavan (Thesis advisor) / Spanias, Andreas (Committee member) / Li, Baoxin (Committee member) / Jayasuriya, Suren (Committee member) / Arizona State University (Publisher)
Created2019
Description
Over the past decade, machine learning research has made great strides and significant impact in several fields. Its success is greatly attributed to the development of effective machine learning algorithms like deep neural networks (a.k.a. deep learning), availability of large-scale databases and access to specialized hardware like Graphic Processing Units. When designing and training machine learning systems, researchers often assume access to large quantities of data that capture different possible variations. Variations in the data is needed to incorporate desired invariance and robustness properties in the machine learning system, especially in the case of deep learning algorithms. However, it is very difficult to gather such data in a real-world setting. For example, in certain medical/healthcare applications, it is very challenging to have access to data from all possible scenarios or with the necessary amount of variations as required to train the system. Additionally, the over-parameterized and unconstrained nature of deep neural networks can cause them to be poorly trained and in many cases over-confident which, in turn, can hamper their reliability and generalizability. This dissertation is a compendium of my research efforts to address the above challenges. I propose building invariant feature representations by wedding concepts from topological data analysis and Riemannian geometry, that automatically incorporate the desired invariance properties for different computer vision applications. I discuss how deep learning can be used to address some of the common challenges faced when working with topological data analysis methods. I describe alternative learning strategies based on unsupervised learning and transfer learning to address issues like dataset shifts and limited training data. Finally, I discuss my preliminary work on applying simple orthogonal constraints on deep learning feature representations to help develop more reliable and better calibrated models.
ContributorsSom, Anirudh (Author) / Turaga, Pavan (Thesis advisor) / Krishnamurthi, Narayanan (Committee member) / Spanias, Andreas (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2020
Description
Open Design is a crowd-driven global ecosystem which tries to challenge and alter contemporary modes of capitalistic hardware production. It strives to build on the collective skills, expertise and efforts of people regardless of their educational, social or political backgrounds to develop and disseminate physical products, machines and systems. In contrast to capitalistic hardware production, Open Design practitioners publicly share design files, blueprints and knowhow through various channels including internet platforms and in-person workshops. These designs are typically replicated, modified, improved and reshared by individuals and groups who are broadly referred to as ‘makers’.
This dissertation aims to expand the current scope of Open Design within human-computer interaction (HCI) research through a long-term exploration of Open Design’s socio-technical processes. I examine Open Design from three perspectives: the functional—materials, tools, and platforms that enable crowd-driven open hardware production, the critical—materially-oriented engagements within open design as a site for sociotechnical discourse, and the speculative—crowd-driven critical envisioning of future hardware.
More specifically, this dissertation first explores the growing global scene of Open Design through a long-term ethnographic study of the open science hardware (OScH) movement, a genre of Open Design. This long-term study of OScH provides a focal point for HCI to deeply understand Open Design's growing global landscape. Second, it examines the application of Critical Making within Open Design through an OScH workshop with designers, engineers, artists and makers from local communities. This work foregrounds the role of HCI researchers as facilitators of collaborative critical engagements within Open Design. Third, this dissertation introduces the concept of crowd-driven Design Fiction through the development of a publicly accessible online Design Fiction platform named Dream Drones. Through a six month long development and a study with drone related practitioners, it offers several pragmatic insights into the challenges and opportunities for crowd-driven Design Fiction. Through these explorations, I highlight the broader implications and novel research pathways for HCI to shape and be shaped by the global Open Design movement.
This dissertation aims to expand the current scope of Open Design within human-computer interaction (HCI) research through a long-term exploration of Open Design’s socio-technical processes. I examine Open Design from three perspectives: the functional—materials, tools, and platforms that enable crowd-driven open hardware production, the critical—materially-oriented engagements within open design as a site for sociotechnical discourse, and the speculative—crowd-driven critical envisioning of future hardware.
More specifically, this dissertation first explores the growing global scene of Open Design through a long-term ethnographic study of the open science hardware (OScH) movement, a genre of Open Design. This long-term study of OScH provides a focal point for HCI to deeply understand Open Design's growing global landscape. Second, it examines the application of Critical Making within Open Design through an OScH workshop with designers, engineers, artists and makers from local communities. This work foregrounds the role of HCI researchers as facilitators of collaborative critical engagements within Open Design. Third, this dissertation introduces the concept of crowd-driven Design Fiction through the development of a publicly accessible online Design Fiction platform named Dream Drones. Through a six month long development and a study with drone related practitioners, it offers several pragmatic insights into the challenges and opportunities for crowd-driven Design Fiction. Through these explorations, I highlight the broader implications and novel research pathways for HCI to shape and be shaped by the global Open Design movement.
ContributorsFernando, Kattak Kuttige Rex Piyum (Author) / Kuznetsov, Anastasia (Thesis advisor) / Turaga, Pavan (Committee member) / Middel, Ariane (Committee member) / Takamura, John (Committee member) / Arizona State University (Publisher)
Created2020
Description
Cameras have become commonplace with wide-ranging applications of phone photography, computer vision, and medical imaging. With a growing need to reduce size and costs while maintaining image quality, the need to look past traditional style of cameras is becoming more apparent. Several non-traditional cameras have shown to be promising options for size-constraint applications, and while they may offer several advantages, they also usually are limited by image quality degradation due to optical or a need to reconstruct a captured image. In this thesis, we take a look at three of these non-traditional cameras: a pinhole camera, a diffusion-mask lensless camera, and an under-display camera (UDC).
For each of these cases, I present a feasible image restoration pipeline to correct for their particular limitations. For the pinhole camera, I present an early pipeline to allow for practical pinhole photography by reducing noise levels caused by low-light imaging, enhancing exposure levels, and sharpening the blur caused by the pinhole. For lensless cameras, we explore a neural network architecture that performs joint image reconstruction and point spread function (PSF) estimation to robustly recover images captured with multiple PSFs from different cameras. Using adversarial learning, this approach achieves improved reconstruction results that do not require explicit knowledge of the PSF at test-time and shows an added improvement in the reconstruction model’s ability to generalize to variations in the camera’s PSF. This allows lensless cameras to be utilized in a wider range of applications that require multiple cameras without the need to explicitly train a separate model for each new camera. For UDCs, we utilize a multi-stage approach to correct for low light transmission, blur, and haze. This pipeline uses a PyNET deep neural network architecture to perform a majority of the restoration, while additionally using a traditional optimization approach which is then fused in a learned manner in the second stage to improve high-frequency features. I show results from this novel fusion approach that is on-par with the state of the art.
For each of these cases, I present a feasible image restoration pipeline to correct for their particular limitations. For the pinhole camera, I present an early pipeline to allow for practical pinhole photography by reducing noise levels caused by low-light imaging, enhancing exposure levels, and sharpening the blur caused by the pinhole. For lensless cameras, we explore a neural network architecture that performs joint image reconstruction and point spread function (PSF) estimation to robustly recover images captured with multiple PSFs from different cameras. Using adversarial learning, this approach achieves improved reconstruction results that do not require explicit knowledge of the PSF at test-time and shows an added improvement in the reconstruction model’s ability to generalize to variations in the camera’s PSF. This allows lensless cameras to be utilized in a wider range of applications that require multiple cameras without the need to explicitly train a separate model for each new camera. For UDCs, we utilize a multi-stage approach to correct for low light transmission, blur, and haze. This pipeline uses a PyNET deep neural network architecture to perform a majority of the restoration, while additionally using a traditional optimization approach which is then fused in a learned manner in the second stage to improve high-frequency features. I show results from this novel fusion approach that is on-par with the state of the art.
ContributorsRego, Joshua D (Author) / Jayasuriya, Suren (Thesis advisor) / Blain Christen, Jennifer (Thesis advisor) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2020
Description
Contact tracing has been shown to be effective in limiting the rate of spread of infectious diseases like COVID-19. Several solutions based on the exchange of random, anonymous tokens between users’ mobile devices via Bluetooth, or using users’ location traces have been proposed and deployed. These solutions require the user device to download the tokens (or traces) of infected users from the server. The user tokens are matched with infected users’ tokens to determine an exposure event. These solutions are vulnerable to a range of security and privacy issues, and require large downloads, thus warranting the need for an efficient protocol with strong privacy guarantees. Moreover, these solutions are based solely on proximity between user devices, while COVID-19 can spread from common surfaces as well. Knowledge of areas with a large number of visits by infected users (hotspots) can help inform users to avoid those areas and thereby reduce surface transmission. This thesis proposes a strong secure system for contact tracing and hotspots histogram computation. The contact tracing protocol uses a combination of Bluetooth Low Energy and Global Positioning System (GPS) location data. A novel and deployment-friendly Delegated Private Set Intersection Cardinality protocol is proposed for efficient and secure server aided matching of tokens. Secure aggregation techniques are used to allow the server to learn areas of high risk from location traces of diagnosed users, without revealing any individual user’s location history.
ContributorsSurana, Chetan (Author) / Trieu, Ni (Thesis advisor) / Sankar, Lalitha (Committee member) / Berisha, Visar (Committee member) / Zhao, Ming (Committee member) / Arizona State University (Publisher)
Created2021
Description
A distributed wireless sensor network (WSN) is a network of a large number of lowcost,multi-functional sensors with power, bandwidth, and memory constraints, operating
in remote environments with sensing and communication capabilities. WSNs
are a source for a large amount of data and due to the inherent communication and
resource constraints, developing a distributed algorithms to perform statistical parameter
estimation and data analysis is necessary. In this work, consensus based
distributed algorithms are developed for distributed estimation and processing over
WSNs. Firstly, a distributed spectral clustering algorithm to group the sensors based
on the location attributes is developed. Next, a distributed max consensus algorithm
robust to additive noise in the network is designed. Furthermore, distributed spectral
radius estimation algorithms for analog, as well as, digital communication models
are developed. The proposed algorithms work for any connected graph topologies.
Theoretical bounds are derived and simulation results supporting the theory are also
presented.
ContributorsMuniraju, Gowtham (Author) / Tepedelenlioğlu, Cihan (Thesis advisor) / Spanias, Andreas (Thesis advisor) / Berisha, Visar (Committee member) / Jayasuriya, Suren (Committee member) / Arizona State University (Publisher)
Created2021