Matching Items (9)
Filtering by
- All Subjects: Computer Science
- Genre: Masters Thesis
Description
Typically, the complete loss or severe impairment of a sense such as vision and/or hearing is compensated through sensory substitution, i.e., the use of an alternative sense for receiving the same information. For individuals who are blind or visually impaired, the alternative senses have predominantly been hearing and touch. For movies, visual content has been made accessible to visually impaired viewers through audio descriptions -- an additional narration that describes scenes, the characters involved and other pertinent details. However, as audio descriptions should not overlap with dialogue, sound effects and musical scores, there is limited time to convey information, often resulting in stunted and abridged descriptions that leave out many important visual cues and concepts. This work proposes a promising multimodal approach to sensory substitution for movies by providing complementary information through haptics, pertaining to the positions and movements of actors, in addition to a film's audio description and audio content. In a ten-minute presentation of five movie clips to ten individuals who were visually impaired or blind, the novel methodology was found to provide an almost two time increase in the perception of actors' movements in scenes. Moreover, participants appreciated and found useful the overall concept of providing a visual perspective to film through haptics.
ContributorsViswanathan, Lakshmie Narayan (Author) / Panchanathan, Sethuraman (Thesis advisor) / Hedgpeth, Terri (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2011
Description
Real-world environments are characterized by non-stationary and continuously evolving data. Learning a classification model on this data would require a framework that is able to adapt itself to newer circumstances. Under such circumstances, transfer learning has come to be a dependable methodology for improving classification performance with reduced training costs and without the need for explicit relearning from scratch. In this thesis, a novel instance transfer technique that adapts a "Cost-sensitive" variation of AdaBoost is presented. The method capitalizes on the theoretical and functional properties of AdaBoost to selectively reuse outdated training instances obtained from a "source" domain to effectively classify unseen instances occurring in a different, but related "target" domain. The algorithm is evaluated on real-world classification problems namely accelerometer based 3D gesture recognition, smart home activity recognition and text categorization. The performance on these datasets is analyzed and evaluated against popular boosting-based instance transfer techniques. In addition, supporting empirical studies, that investigate some of the less explored bottlenecks of boosting based instance transfer methods, are presented, to understand the suitability and effectiveness of this form of knowledge transfer.
ContributorsVenkatesan, Ashok (Author) / Panchanathan, Sethuraman (Thesis advisor) / Li, Baoxin (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2011
Description
Machine learning models convert raw data in the form of video, images, audio,
text, etc. into feature representations that are convenient for computational process-
ing. Deep neural networks have proven to be very efficient feature extractors for a
variety of machine learning tasks. Generative models based on deep neural networks
introduce constraints on the feature space to learn transferable and disentangled rep-
resentations. Transferable feature representations help in training machine learning
models that are robust across different distributions of data. For example, with the
application of transferable features in domain adaptation, models trained on a source
distribution can be applied to a data from a target distribution even though the dis-
tributions may be different. In style transfer and image-to-image translation, disen-
tangled representations allow for the separation of style and content when translating
images.
This thesis examines learning transferable data representations in novel deep gen-
erative models. The Semi-Supervised Adversarial Translator (SAT) utilizes adversar-
ial methods and cross-domain weight sharing in a neural network to extract trans-
ferable representations. These transferable interpretations can then be decoded into
the original image or a similar image in another domain. The Explicit Disentangling
Network (EDN) utilizes generative methods to disentangle images into their core at-
tributes and then segments sets of related attributes. The EDN can separate these
attributes by controlling the ow of information using a novel combination of losses
and network architecture. This separation of attributes allows precise modi_cations
to speci_c components of the data representation, boosting the performance of ma-
chine learning tasks. The effectiveness of these models is evaluated across domain
adaptation, style transfer, and image-to-image translation tasks.
text, etc. into feature representations that are convenient for computational process-
ing. Deep neural networks have proven to be very efficient feature extractors for a
variety of machine learning tasks. Generative models based on deep neural networks
introduce constraints on the feature space to learn transferable and disentangled rep-
resentations. Transferable feature representations help in training machine learning
models that are robust across different distributions of data. For example, with the
application of transferable features in domain adaptation, models trained on a source
distribution can be applied to a data from a target distribution even though the dis-
tributions may be different. In style transfer and image-to-image translation, disen-
tangled representations allow for the separation of style and content when translating
images.
This thesis examines learning transferable data representations in novel deep gen-
erative models. The Semi-Supervised Adversarial Translator (SAT) utilizes adversar-
ial methods and cross-domain weight sharing in a neural network to extract trans-
ferable representations. These transferable interpretations can then be decoded into
the original image or a similar image in another domain. The Explicit Disentangling
Network (EDN) utilizes generative methods to disentangle images into their core at-
tributes and then segments sets of related attributes. The EDN can separate these
attributes by controlling the ow of information using a novel combination of losses
and network architecture. This separation of attributes allows precise modi_cations
to speci_c components of the data representation, boosting the performance of ma-
chine learning tasks. The effectiveness of these models is evaluated across domain
adaptation, style transfer, and image-to-image translation tasks.
ContributorsEusebio, Jose Miguel Ang (Author) / Panchanathan, Sethuraman (Thesis advisor) / Davulcu, Hasan (Committee member) / Venkateswara, Hemanth (Committee member) / Arizona State University (Publisher)
Created2018
Description
Research literature was reviewed to find recommended tools and technologies for operating Unmanned Aerial Systems (UAS) fleets in an urban environment. However, restrictive legislation prohibits fully autonomous flight without an operator. Existing literature covers considerations for operating UAS fleets in a controlled environment, with an emphasis on the effect different networking approaches have on the topology of the UAS network. The primary network topology used to implement UAS communications is 802.11 protocols, which can transmit telemetry and a video stream using off the shelf hardware. Other implementations use low-frequency radios for long distance communication, or higher latency 4G LTE modems to access existing network infrastructure. However, a gap remains testing different network topologies outside of a controlled environment.
With the correct permits in place, further research can explore how different UAS network topologies behave in an urban environment when implemented with off the shelf UAS hardware. In addition to testing different network topologies, this thesis covers the implementation of building a secure, scalable system using modern cloud computation tools and services capable of supporting a variable number of UAS. The system also supports the end-to-end simulation of the system considering factors such as battery life and realistic UAS kinematics. The implementation of the system leads to new findings needed to deploy UAS fleets in urban environments.
With the correct permits in place, further research can explore how different UAS network topologies behave in an urban environment when implemented with off the shelf UAS hardware. In addition to testing different network topologies, this thesis covers the implementation of building a secure, scalable system using modern cloud computation tools and services capable of supporting a variable number of UAS. The system also supports the end-to-end simulation of the system considering factors such as battery life and realistic UAS kinematics. The implementation of the system leads to new findings needed to deploy UAS fleets in urban environments.
ContributorsD'Souza, Daniel (Author) / Panchanathan, Sethuraman (Thesis advisor) / Berman, Spring (Committee member) / Zhang, Yu (Committee member) / Arizona State University (Publisher)
Created2018
Description
Endowing machines with the ability to understand digital images is a critical task for a host of high-impact applications, including pathology detection in radiographic imaging, autonomous vehicles, and assistive technology for the visually impaired. Computer vision systems rely on large corpora of annotated data in order to train task-specific visual recognition models. Despite significant advances made over the past decade, the fact remains collecting and annotating the data needed to successfully train a model is a prohibitively expensive endeavor. Moreover, these models are prone to rapid performance degradation when applied to data sampled from a different domain. Recent works in the development of deep adaptation networks seek to overcome these challenges by facilitating transfer learning between source and target domains. In parallel, the unification of dominant semi-supervised learning techniques has illustrated unprecedented potential for utilizing unlabeled data to train classification models in defiance of discouragingly meager sets of annotated data.
In this thesis, a novel domain adaptation algorithm -- Domain Adaptive Fusion (DAF) -- is proposed, which encourages a domain-invariant linear relationship between the pixel-space of different domains and the prediction-space while being trained under a domain adversarial signal. The thoughtful combination of key components in unsupervised domain adaptation and semi-supervised learning enable DAF to effectively bridge the gap between source and target domains. Experiments performed on computer vision benchmark datasets for domain adaptation endorse the efficacy of this hybrid approach, outperforming all of the baseline architectures on most of the transfer tasks.
In this thesis, a novel domain adaptation algorithm -- Domain Adaptive Fusion (DAF) -- is proposed, which encourages a domain-invariant linear relationship between the pixel-space of different domains and the prediction-space while being trained under a domain adversarial signal. The thoughtful combination of key components in unsupervised domain adaptation and semi-supervised learning enable DAF to effectively bridge the gap between source and target domains. Experiments performed on computer vision benchmark datasets for domain adaptation endorse the efficacy of this hybrid approach, outperforming all of the baseline architectures on most of the transfer tasks.
ContributorsDudley, Andrew, M.S (Author) / Panchanathan, Sethuraman (Thesis advisor) / Venkateswara, Hemanth (Committee member) / McDaniel, Troy (Committee member) / Arizona State University (Publisher)
Created2019
Description
Playlists have become a significant part of the music listening experience today because of the digital cloud-based services such as Spotify, Pandora, Apple Music. Owing to the meteoric rise in usage of playlists, recommending playlists is crucial to music services today. Although there has been a lot of work done in playlist prediction, the area of playlist representation hasn't received that level of attention. Over the last few years, sequence-to-sequence models, especially in the field of natural language processing have shown the effectiveness of learned embeddings in capturing the semantic characteristics of sequences. Similar concepts can be applied to music to learn fixed length representations for playlists and the learned representations can then be used for downstream tasks such as playlist comparison and recommendation.
In this thesis, the problem of learning a fixed-length representation is formulated in an unsupervised manner, using Neural Machine Translation (NMT), where playlists are interpreted as sentences and songs as words. This approach is compared with other encoding architectures and evaluated using the suite of tasks commonly used for evaluating sentence embeddings, along with a few additional tasks pertaining to music. The aim of the evaluation is to study the traits captured by the playlist embeddings such that these can be leveraged for music recommendation purposes. This work lays down the foundation for analyzing music playlists and learning the patterns that exist in the playlists in an end-to-end manner. This thesis finally concludes with a discussion on the future direction for this research and its potential impact in the domain of Music Information Retrieval.
In this thesis, the problem of learning a fixed-length representation is formulated in an unsupervised manner, using Neural Machine Translation (NMT), where playlists are interpreted as sentences and songs as words. This approach is compared with other encoding architectures and evaluated using the suite of tasks commonly used for evaluating sentence embeddings, along with a few additional tasks pertaining to music. The aim of the evaluation is to study the traits captured by the playlist embeddings such that these can be leveraged for music recommendation purposes. This work lays down the foundation for analyzing music playlists and learning the patterns that exist in the playlists in an end-to-end manner. This thesis finally concludes with a discussion on the future direction for this research and its potential impact in the domain of Music Information Retrieval.
ContributorsPapreja, Piyush (Author) / Panchanathan, Sethuraman (Thesis advisor) / Demakethepalli Venkateswara, Hemanth Kumar (Committee member) / Amor, Heni Ben (Committee member) / Arizona State University (Publisher)
Created2019
Description
Humans perceive the environment using multiple modalities like vision, speech (language), touch, taste, and smell. The knowledge obtained from one modality usually complements the other. Learning through several modalities helps in constructing an accurate model of the environment. Most of the current vision and language models are modality-specific and, in many cases, extensively use deep-learning based attention mechanisms for learning powerful representations. This work discusses the role of attention in associating vision and language for generating shared representation. Language Image Transformer (LIT) is proposed for learning multi-modal representations of the environment. It uses a training objective based on Contrastive Predictive Coding (CPC) to maximize the Mutual Information (MI) between the visual and linguistic representations. It learns the relationship between the modalities using the proposed cross-modal attention layers. It is trained and evaluated using captioning datasets, MS COCO, and Conceptual Captions. The results and the analysis offers a perspective on the use of Mutual Information Maximisation (MIM) for generating generalizable representations across multiple modalities.
ContributorsRamakrishnan, Raghavendran (Author) / Panchanathan, Sethuraman (Thesis advisor) / Venkateswara, Hemanth Kumar (Thesis advisor) / McDaniel, Troy (Committee member) / Arizona State University (Publisher)
Created2020
Description
In the last decade deep learning based models have revolutionized machine learning and computer vision applications. However, these models are data-hungry and training them is a time-consuming process. In addition, when deep neural networks are updated to augment their prediction space with new data, they run into the problem of catastrophic forgetting, where the model forgets previously learned knowledge as it overfits to the newly available data. Incremental learning algorithms enable deep neural networks to prevent catastrophic forgetting by retaining knowledge of previously observed data while also learning from newly available data.
This thesis presents three models for incremental learning; (i) Design of an algorithm for generative incremental learning using a pre-trained deep neural network classifier; (ii) Development of a hashing based clustering algorithm for efficient incremental learning; (iii) Design of a student-teacher coupled neural network to distill knowledge for incremental learning. The proposed algorithms were evaluated using popular vision datasets for classification tasks. The thesis concludes with a discussion about the feasibility of using these techniques to transfer information between networks and also for incremental learning applications.
This thesis presents three models for incremental learning; (i) Design of an algorithm for generative incremental learning using a pre-trained deep neural network classifier; (ii) Development of a hashing based clustering algorithm for efficient incremental learning; (iii) Design of a student-teacher coupled neural network to distill knowledge for incremental learning. The proposed algorithms were evaluated using popular vision datasets for classification tasks. The thesis concludes with a discussion about the feasibility of using these techniques to transfer information between networks and also for incremental learning applications.
ContributorsPatil, Rishabh (Author) / Venkateswara, Hemanth (Thesis advisor) / Panchanathan, Sethuraman (Thesis advisor) / McDaniel, Troy (Committee member) / Arizona State University (Publisher)
Created2020
Description
Humans have a great ability to recognize objects in different environments irrespective of their variations. However, the same does not apply to machine learning models which are unable to generalize to images of objects from different domains. The generalization of these models to new data is constrained by the domain gap. Many factors such as image background, image resolution, color, camera perspective and variations in the objects are responsible for the domain gap between the training data (source domain) and testing data (target domain). Domain adaptation algorithms aim to overcome the domain gap between the source and target domains and learn robust models that can perform well across both the domains.
This thesis provides solutions for the standard problem of unsupervised domain adaptation (UDA) and the more generic problem of generalized domain adaptation (GDA). The contributions of this thesis are as follows. (1) Certain and Consistent Domain Adaptation model for closed-set unsupervised domain adaptation by aligning the features of the source and target domain using deep neural networks. (2) A multi-adversarial deep learning model for generalized domain adaptation. (3) A gating model that detects out-of-distribution samples for generalized domain adaptation.
The models were tested across multiple computer vision datasets for domain adaptation.
The dissertation concludes with a discussion on the proposed approaches and future directions for research in closed set and generalized domain adaptation.
This thesis provides solutions for the standard problem of unsupervised domain adaptation (UDA) and the more generic problem of generalized domain adaptation (GDA). The contributions of this thesis are as follows. (1) Certain and Consistent Domain Adaptation model for closed-set unsupervised domain adaptation by aligning the features of the source and target domain using deep neural networks. (2) A multi-adversarial deep learning model for generalized domain adaptation. (3) A gating model that detects out-of-distribution samples for generalized domain adaptation.
The models were tested across multiple computer vision datasets for domain adaptation.
The dissertation concludes with a discussion on the proposed approaches and future directions for research in closed set and generalized domain adaptation.
ContributorsNagabandi, Bhadrinath (Author) / Panchanathan, Sethuraman (Thesis advisor) / Venkateswara, Hemanth (Thesis advisor) / McDaniel, Troy (Committee member) / Arizona State University (Publisher)
Created2020