Matching Items (13)
Filtering by
- All Subjects: deep learning
- Creators: Yang, Yezhou
Description
Computer Vision as a eld has gone through signicant changes in the last decade.
The eld has seen tremendous success in designing learning systems with hand-crafted
features and in using representation learning to extract better features. In this dissertation
some novel approaches to representation learning and task learning are studied.
Multiple-instance learning which is generalization of supervised learning, is one
example of task learning that is discussed. In particular, a novel non-parametric k-
NN-based multiple-instance learning is proposed, which is shown to outperform other
existing approaches. This solution is applied to a diabetic retinopathy pathology
detection problem eectively.
In cases of representation learning, generality of neural features are investigated
rst. This investigation leads to some critical understanding and results in feature
generality among datasets. The possibility of learning from a mentor network instead
of from labels is then investigated. Distillation of dark knowledge is used to eciently
mentor a small network from a pre-trained large mentor network. These studies help
in understanding representation learning with smaller and compressed networks.
The eld has seen tremendous success in designing learning systems with hand-crafted
features and in using representation learning to extract better features. In this dissertation
some novel approaches to representation learning and task learning are studied.
Multiple-instance learning which is generalization of supervised learning, is one
example of task learning that is discussed. In particular, a novel non-parametric k-
NN-based multiple-instance learning is proposed, which is shown to outperform other
existing approaches. This solution is applied to a diabetic retinopathy pathology
detection problem eectively.
In cases of representation learning, generality of neural features are investigated
rst. This investigation leads to some critical understanding and results in feature
generality among datasets. The possibility of learning from a mentor network instead
of from labels is then investigated. Distillation of dark knowledge is used to eciently
mentor a small network from a pre-trained large mentor network. These studies help
in understanding representation learning with smaller and compressed networks.
ContributorsVenkatesan, Ragav (Author) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Yang, Yezhou (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2017
Description
The performance of most of the visual computing tasks depends on the quality of the features extracted from the raw data. Insightful feature representation increases the performance of many learning algorithms by exposing the underlying explanatory factors of the output for the unobserved input. A good representation should also handle anomalies in the data such as missing samples and noisy input caused by the undesired, external factors of variation. It should also reduce the data redundancy. Over the years, many feature extraction processes have been invented to produce good representations of raw images and videos.
The feature extraction processes can be categorized into three groups. The first group contains processes that are hand-crafted for a specific task. Hand-engineering features requires the knowledge of domain experts and manual labor. However, the feature extraction process is interpretable and explainable. Next group contains the latent-feature extraction processes. While the original feature lies in a high-dimensional space, the relevant factors for a task often lie on a lower dimensional manifold. The latent-feature extraction employs hidden variables to expose the underlying data properties that cannot be directly measured from the input. Latent features seek a specific structure such as sparsity or low-rank into the derived representation through sophisticated optimization techniques. The last category is that of deep features. These are obtained by passing raw input data with minimal pre-processing through a deep network. Its parameters are computed by iteratively minimizing a task-based loss.
In this dissertation, I present four pieces of work where I create and learn suitable data representations. The first task employs hand-crafted features to perform clinically-relevant retrieval of diabetic retinopathy images. The second task uses latent features to perform content-adaptive image enhancement. The third task ranks a pair of images based on their aestheticism. The goal of the last task is to capture localized image artifacts in small datasets with patch-level labels. For both these tasks, I propose novel deep architectures and show significant improvement over the previous state-of-art approaches. A suitable combination of feature representations augmented with an appropriate learning approach can increase performance for most visual computing tasks.
The feature extraction processes can be categorized into three groups. The first group contains processes that are hand-crafted for a specific task. Hand-engineering features requires the knowledge of domain experts and manual labor. However, the feature extraction process is interpretable and explainable. Next group contains the latent-feature extraction processes. While the original feature lies in a high-dimensional space, the relevant factors for a task often lie on a lower dimensional manifold. The latent-feature extraction employs hidden variables to expose the underlying data properties that cannot be directly measured from the input. Latent features seek a specific structure such as sparsity or low-rank into the derived representation through sophisticated optimization techniques. The last category is that of deep features. These are obtained by passing raw input data with minimal pre-processing through a deep network. Its parameters are computed by iteratively minimizing a task-based loss.
In this dissertation, I present four pieces of work where I create and learn suitable data representations. The first task employs hand-crafted features to perform clinically-relevant retrieval of diabetic retinopathy images. The second task uses latent features to perform content-adaptive image enhancement. The third task ranks a pair of images based on their aestheticism. The goal of the last task is to capture localized image artifacts in small datasets with patch-level labels. For both these tasks, I propose novel deep architectures and show significant improvement over the previous state-of-art approaches. A suitable combination of feature representations augmented with an appropriate learning approach can increase performance for most visual computing tasks.
ContributorsChandakkar, Parag Shridhar (Author) / Li, Baoxin (Thesis advisor) / Yang, Yezhou (Committee member) / Turaga, Pavan (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2017
Description
Rapid intraoperative diagnosis of brain tumors is of great importance for planning treatment and guiding the surgeon about the extent of resection. Currently, the standard for the preliminary intraoperative tissue analysis is frozen section biopsy that has major limitations such as tissue freezing and cutting artifacts, sampling errors, lack of immediate interaction between the pathologist and the surgeon, and time consuming.
Handheld, portable confocal laser endomicroscopy (CLE) is being explored in neurosurgery for its ability to image histopathological features of tissue at cellular resolution in real time during brain tumor surgery. Over the course of examination of the surgical tumor resection, hundreds to thousands of images may be collected. The high number of images requires significant time and storage load for subsequent reviewing, which motivated several research groups to employ deep convolutional neural networks (DCNNs) to improve its utility during surgery. DCNNs have proven to be useful in natural and medical image analysis tasks such as classification, object detection, and image segmentation.
This thesis proposes using DCNNs for analyzing CLE images of brain tumors. Particularly, it explores the practicality of DCNNs in three main tasks. First, off-the shelf DCNNs were used to classify images into diagnostic and non-diagnostic. Further experiments showed that both ensemble modeling and transfer learning improved the classifier’s accuracy in evaluating the diagnostic quality of new images at test stage. Second, a weakly-supervised learning pipeline was developed for localizing key features of diagnostic CLE images from gliomas. Third, image style transfer was used to improve the diagnostic quality of CLE images from glioma tumors by transforming the histology patterns in CLE images of fluorescein sodium-stained tissue into the ones in conventional hematoxylin and eosin-stained tissue slides.
These studies suggest that DCNNs are opted for analysis of CLE images. They may assist surgeons in sorting out the non-diagnostic images, highlighting the key regions and enhancing their appearance through pattern transformation in real time. With recent advances in deep learning such as generative adversarial networks and semi-supervised learning, new research directions need to be followed to discover more promises of DCNNs in CLE image analysis.
Handheld, portable confocal laser endomicroscopy (CLE) is being explored in neurosurgery for its ability to image histopathological features of tissue at cellular resolution in real time during brain tumor surgery. Over the course of examination of the surgical tumor resection, hundreds to thousands of images may be collected. The high number of images requires significant time and storage load for subsequent reviewing, which motivated several research groups to employ deep convolutional neural networks (DCNNs) to improve its utility during surgery. DCNNs have proven to be useful in natural and medical image analysis tasks such as classification, object detection, and image segmentation.
This thesis proposes using DCNNs for analyzing CLE images of brain tumors. Particularly, it explores the practicality of DCNNs in three main tasks. First, off-the shelf DCNNs were used to classify images into diagnostic and non-diagnostic. Further experiments showed that both ensemble modeling and transfer learning improved the classifier’s accuracy in evaluating the diagnostic quality of new images at test stage. Second, a weakly-supervised learning pipeline was developed for localizing key features of diagnostic CLE images from gliomas. Third, image style transfer was used to improve the diagnostic quality of CLE images from glioma tumors by transforming the histology patterns in CLE images of fluorescein sodium-stained tissue into the ones in conventional hematoxylin and eosin-stained tissue slides.
These studies suggest that DCNNs are opted for analysis of CLE images. They may assist surgeons in sorting out the non-diagnostic images, highlighting the key regions and enhancing their appearance through pattern transformation in real time. With recent advances in deep learning such as generative adversarial networks and semi-supervised learning, new research directions need to be followed to discover more promises of DCNNs in CLE image analysis.
ContributorsIzady Yazdanabadi, Mohammadhassan (Author) / Preul, Mark (Thesis advisor) / Yang, Yezhou (Thesis advisor) / Nakaji, Peter (Committee member) / Vernon, Brent (Committee member) / Arizona State University (Publisher)
Created2019
Description
Students learn in various ways \u2014 visualization, auditory, memorizing, or making analogies. Traditional lecturing in engineering courses and the learning styles of engineering students are inharmonious causing students to be at a disadvantage based on their learning style (Felder & Silverman, 1988). My study analyzes the traditional approach to learning coding skills which is unnatural to engineering students with no previous exposure and examining if visual learning enhances introductory computer science education. Visual and text-based learning are evaluated to determine how students learn introductory coding skills and associated problem solving skills. My study was conducted to observe how the two types of learning aid the students in learning how to problem solve as well as how much knowledge can be obtained in a short period of time. The application used for visual learning was Scratch and Repl.it was used for text-based learning. Two exams were made to measure the progress made by each student. The topics covered by the exam were initialization, variable reassignment, output, if statements, if else statements, nested if statements, logical operators, arrays/lists, while loop, type casting, functions, object orientation, and sorting. Analysis of the data collected in the study allow us to observe whether the traditional method of teaching programming or block-based programming is more beneficial and in what topics of introductory computer science concepts.
ContributorsVidaure, Destiny Vanessa (Author) / Meuth, Ryan (Thesis director) / Yang, Yezhou (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
To ensure system integrity, robots need to proactively avoid any unwanted physical perturbation that may cause damage to the underlying hardware. In this thesis work, we investigate a machine learning approach that allows robots to anticipate impending physical perturbations from perceptual cues. In contrast to other approaches that require knowledge about sources of perturbation to be encoded before deployment, our method is based on experiential learning. Robots learn to associate visual cues with subsequent physical perturbations and contacts. In turn, these extracted visual cues are then used to predict potential future perturbations acting on the robot. To this end, we introduce a novel deep network architecture which combines multiple sub- networks for dealing with robot dynamics and perceptual input from the environment. We present a self-supervised approach for training the system that does not require any labeling of training data. Extensive experiments in a human-robot interaction task show that a robot can learn to predict physical contact by a human interaction partner without any prior information or labeling. Furthermore, the network is able to successfully predict physical contact from either depth stream input or traditional video input or using both modalities as input.
ContributorsSur, Indranil (Author) / Amor, Heni B (Thesis advisor) / Fainekos, Georgios (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2017
Description
Compressive sensing theory allows to sense and reconstruct signals/images with lower sampling rate than Nyquist rate. Applications in resource constrained environment stand to benefit from this theory, opening up many possibilities for new applications at the same time. The traditional inference pipeline for computer vision sequence reconstructing the image from compressive measurements. However,the reconstruction process is a computationally expensive step that also provides poor results at high compression rate. There have been several successful attempts to perform inference tasks directly on compressive measurements such as activity recognition. In this thesis, I am interested to tackle a more challenging vision problem - Visual question answering (VQA) without reconstructing the compressive images. I investigate the feasibility of this problem with a series of experiments, and I evaluate proposed methods on a VQA dataset and discuss promising results and direction for future work.
ContributorsHuang, Li-Chin (Author) / Turaga, Pavan (Thesis advisor) / Yang, Yezhou (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2017
Description
Light field imaging is limited in its computational processing demands of high
sampling for both spatial and angular dimensions. Single-shot light field cameras
sacrifice spatial resolution to sample angular viewpoints, typically by multiplexing
incoming rays onto a 2D sensor array. While this resolution can be recovered using
compressive sensing, these iterative solutions are slow in processing a light field. We
present a deep learning approach using a new, two branch network architecture,
consisting jointly of an autoencoder and a 4D CNN, to recover a high resolution
4D light field from a single coded 2D image. This network decreases reconstruction
time significantly while achieving average PSNR values of 26-32 dB on a variety of
light fields. In particular, reconstruction time is decreased from 35 minutes to 6.7
minutes as compared to the dictionary method for equivalent visual quality. These
reconstructions are performed at small sampling/compression ratios as low as 8%,
allowing for cheaper coded light field cameras. We test our network reconstructions
on synthetic light fields, simulated coded measurements of real light fields captured
from a Lytro Illum camera, and real coded images from a custom CMOS diffractive
light field camera. The combination of compressive light field capture with deep
learning allows the potential for real-time light field video acquisition systems in the
future.
sampling for both spatial and angular dimensions. Single-shot light field cameras
sacrifice spatial resolution to sample angular viewpoints, typically by multiplexing
incoming rays onto a 2D sensor array. While this resolution can be recovered using
compressive sensing, these iterative solutions are slow in processing a light field. We
present a deep learning approach using a new, two branch network architecture,
consisting jointly of an autoencoder and a 4D CNN, to recover a high resolution
4D light field from a single coded 2D image. This network decreases reconstruction
time significantly while achieving average PSNR values of 26-32 dB on a variety of
light fields. In particular, reconstruction time is decreased from 35 minutes to 6.7
minutes as compared to the dictionary method for equivalent visual quality. These
reconstructions are performed at small sampling/compression ratios as low as 8%,
allowing for cheaper coded light field cameras. We test our network reconstructions
on synthetic light fields, simulated coded measurements of real light fields captured
from a Lytro Illum camera, and real coded images from a custom CMOS diffractive
light field camera. The combination of compressive light field capture with deep
learning allows the potential for real-time light field video acquisition systems in the
future.
ContributorsGupta, Mayank (Author) / Turaga, Pavan (Thesis advisor) / Yang, Yezhou (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2017
Description
Millions of users leave digital traces of their political engagements on social media platforms every day. Users form networks of interactions, produce textual content, like and share each others' content. This creates an invaluable opportunity to better understand the political engagements of internet users. In this proposal, I present three algorithmic solutions to three facets of online political networks; namely, detection of communities, antagonisms and the impact of certain types of accounts on political polarization. First, I develop a multi-view community detection algorithm to find politically pure communities. I find that word usage among other content types (i.e. hashtags, URLs) complement user interactions the best in accurately detecting communities.
Second, I focus on detecting negative linkages between politically motivated social media users. Major social media platforms do not facilitate their users with built-in negative interaction options. However, many political network analysis tasks rely on not only positive but also negative linkages. Here, I present the SocLSFact framework to detect negative linkages among social media users. It utilizes three pieces of information; sentiment cues of textual interactions, positive interactions, and socially balanced triads. I evaluate the contribution of each three aspects in negative link detection performance on multiple tasks.
Third, I propose an experimental setup that quantifies the polarization impact of automated accounts on Twitter retweet networks. I focus on a dataset of tragic Parkland shooting event and its aftermath. I show that when automated accounts are removed from the retweet network the network polarization decrease significantly, while a same number of accounts to the automated accounts are removed randomly the difference is not significant. I also find that prominent predictors of engagement of automatically generated content is not very different than what previous studies point out in general engaging content on social media. Last but not least, I identify accounts which self-disclose their automated nature in their profile by using expressions such as bot, chat-bot, or robot. I find that human engagement to self-disclosing accounts compared to non-disclosing automated accounts is much smaller. This observational finding can motivate further efforts into automated account detection research to prevent their unintended impact.
Second, I focus on detecting negative linkages between politically motivated social media users. Major social media platforms do not facilitate their users with built-in negative interaction options. However, many political network analysis tasks rely on not only positive but also negative linkages. Here, I present the SocLSFact framework to detect negative linkages among social media users. It utilizes three pieces of information; sentiment cues of textual interactions, positive interactions, and socially balanced triads. I evaluate the contribution of each three aspects in negative link detection performance on multiple tasks.
Third, I propose an experimental setup that quantifies the polarization impact of automated accounts on Twitter retweet networks. I focus on a dataset of tragic Parkland shooting event and its aftermath. I show that when automated accounts are removed from the retweet network the network polarization decrease significantly, while a same number of accounts to the automated accounts are removed randomly the difference is not significant. I also find that prominent predictors of engagement of automatically generated content is not very different than what previous studies point out in general engaging content on social media. Last but not least, I identify accounts which self-disclose their automated nature in their profile by using expressions such as bot, chat-bot, or robot. I find that human engagement to self-disclosing accounts compared to non-disclosing automated accounts is much smaller. This observational finding can motivate further efforts into automated account detection research to prevent their unintended impact.
ContributorsOzer, Mert (Author) / Davulcu, Hasan (Thesis advisor) / Liu, Huan (Committee member) / Sen, Arunabha (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2019
Description
In this thesis, I present two new datasets and a modification to the existing models in the form of a novel attention mechanism for Natural Language Inference (NLI). The new datasets have been carefully synthesized from various existing corpora released for different tasks.
The task of NLI is to determine the possibility of a sentence referred to as “Hypothesis” being true given that another sentence referred to as “Premise” is true. In other words, the task is to identify whether the “Premise” entails, contradicts or remains neutral with regards to the “Hypothesis”. NLI is a precursor to solving many Natural Language Processing (NLP) tasks such as Question Answering and Semantic Search. For example, in Question Answering systems, the question is paraphrased to form a declarative statement which is treated as the hypothesis. The options are treated as the premise. The option with the maximum entailment score is considered as the answer. Considering the applications of NLI, the importance of having a strong NLI system can't be stressed enough.
Many large-scale datasets and models have been released in order to advance the field of NLI. While all of these models do get good accuracy on the test sets of the datasets they were trained on, they fail to capture the basic understanding of “Entities” and “Roles”. They often make the mistake of inferring that “John went to the market.” from “Peter went to the market.” failing to capture the notion of “Entities”. In other cases, these models don't understand the difference in the “Roles” played by the same entities in “Premise” and “Hypothesis” sentences and end up wrongly inferring that “Peter drove John to the stadium.” from “John drove Peter to the stadium.”
The lack of understanding of “Roles” can be attributed to the lack of such examples in the various existing datasets. The reason for the existing model’s failure in capturing the notion of “Entities” is not just due to the lack of such examples in the existing NLI datasets. It can also be attributed to the strict use of vector similarity in the “word-to-word” attention mechanism being used in the existing architectures.
To overcome these issues, I present two new datasets to help make the NLI systems capture the notion of “Entities” and “Roles”. The “NER Changed” (NC) dataset and the “Role-Switched” (RS) dataset contains examples of Premise-Hypothesis pairs that require the understanding of “Entities” and “Roles” respectively in order to be able to make correct inferences. This work shows how the existing architectures perform poorly on the “NER Changed” (NC) dataset even after being trained on the new datasets. In order to help the existing architectures, understand the notion of “Entities”, this work proposes a modification to the “word-to-word” attention mechanism. Instead of relying on vector similarity alone, the modified architectures learn to incorporate the “Symbolic Similarity” as well by using the Named-Entity features of the Premise and Hypothesis sentences. The new modified architectures not only perform significantly better than the unmodified architectures on the “NER Changed” (NC) dataset but also performs as well on the existing datasets.
The task of NLI is to determine the possibility of a sentence referred to as “Hypothesis” being true given that another sentence referred to as “Premise” is true. In other words, the task is to identify whether the “Premise” entails, contradicts or remains neutral with regards to the “Hypothesis”. NLI is a precursor to solving many Natural Language Processing (NLP) tasks such as Question Answering and Semantic Search. For example, in Question Answering systems, the question is paraphrased to form a declarative statement which is treated as the hypothesis. The options are treated as the premise. The option with the maximum entailment score is considered as the answer. Considering the applications of NLI, the importance of having a strong NLI system can't be stressed enough.
Many large-scale datasets and models have been released in order to advance the field of NLI. While all of these models do get good accuracy on the test sets of the datasets they were trained on, they fail to capture the basic understanding of “Entities” and “Roles”. They often make the mistake of inferring that “John went to the market.” from “Peter went to the market.” failing to capture the notion of “Entities”. In other cases, these models don't understand the difference in the “Roles” played by the same entities in “Premise” and “Hypothesis” sentences and end up wrongly inferring that “Peter drove John to the stadium.” from “John drove Peter to the stadium.”
The lack of understanding of “Roles” can be attributed to the lack of such examples in the various existing datasets. The reason for the existing model’s failure in capturing the notion of “Entities” is not just due to the lack of such examples in the existing NLI datasets. It can also be attributed to the strict use of vector similarity in the “word-to-word” attention mechanism being used in the existing architectures.
To overcome these issues, I present two new datasets to help make the NLI systems capture the notion of “Entities” and “Roles”. The “NER Changed” (NC) dataset and the “Role-Switched” (RS) dataset contains examples of Premise-Hypothesis pairs that require the understanding of “Entities” and “Roles” respectively in order to be able to make correct inferences. This work shows how the existing architectures perform poorly on the “NER Changed” (NC) dataset even after being trained on the new datasets. In order to help the existing architectures, understand the notion of “Entities”, this work proposes a modification to the “word-to-word” attention mechanism. Instead of relying on vector similarity alone, the modified architectures learn to incorporate the “Symbolic Similarity” as well by using the Named-Entity features of the Premise and Hypothesis sentences. The new modified architectures not only perform significantly better than the unmodified architectures on the “NER Changed” (NC) dataset but also performs as well on the existing datasets.
ContributorsShrivastava, Ishan (Author) / Baral, Chitta (Thesis advisor) / Anwar, Saadat (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2019
Description
Robot motion planning requires computing a sequence of waypoints from an initial configuration of the robot to the goal configuration. Solving a motion planning problem optimally is proven to be NP-Complete. Sampling-based motion planners efficiently compute an approximation of the optimal solution. They sample the configuration space uniformly and hence fail to sample regions of the environment that have narrow passages or pinch points. These critical regions are analogous to landmarks from planning literature as the robot is required to pass through them to reach the goal.
This work proposes a deep learning approach that identifies critical regions in the environment and learns a sampling distribution to effectively sample them in high dimensional configuration spaces.
A classification-based approach is used to learn the distributions. The robot degrees of freedom (DOF) limits are binned and a distribution is generated from sampling motion plan solutions. Conditional information like goal configuration and robot location encoded in the network inputs showcase the network learning to bias the identified critical regions towards the goal configuration. Empirical evaluations are performed against the state of the art sampling-based motion planners on a variety of tasks requiring the robot to pass through critical regions. An empirical analysis of robotic systems with three to eight degrees of freedom indicates that this approach effectively improves planning performance.
This work proposes a deep learning approach that identifies critical regions in the environment and learns a sampling distribution to effectively sample them in high dimensional configuration spaces.
A classification-based approach is used to learn the distributions. The robot degrees of freedom (DOF) limits are binned and a distribution is generated from sampling motion plan solutions. Conditional information like goal configuration and robot location encoded in the network inputs showcase the network learning to bias the identified critical regions towards the goal configuration. Empirical evaluations are performed against the state of the art sampling-based motion planners on a variety of tasks requiring the robot to pass through critical regions. An empirical analysis of robotic systems with three to eight degrees of freedom indicates that this approach effectively improves planning performance.
ContributorsSrinet, Abhyudaya (Author) / Srivastava, Siddharth (Thesis advisor) / Zhang, Yu (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2020