Matching Items (72)
Filtering by
- Genre: Masters Thesis
- Creators: Yang, Yezhou
Description
Feature embeddings differ from raw features in the sense that the former obey certain properties like notion of similarity/dissimilarity in it's embedding space. word2vec is a preeminent example in this direction, where the similarity in the embedding space is measured in terms of the cosine similarity. Such language embedding models have seen numerous applications in both language and vision community as they capture the information in the modality (English language) efficiently. Inspired by these language models, this work focuses on learning embedding spaces for two visual computing tasks, 1. Image Hashing 2. Zero Shot Learning. The training set was used to learn embedding spaces over which similarity/dissimilarity is measured using several distance metrics like hamming / euclidean / cosine distances. While the above-mentioned language models learn generic word embeddings, in this work task specific embeddings were learnt which can be used for Image Retrieval and Classification separately.
Image Hashing is the task of mapping images to binary codes such that some notion of user-defined similarity is preserved. The first part of this work focuses on designing a new framework that uses the hash-tags associated with web images to learn the binary codes. Such codes can be used in several applications like Image Retrieval and Image Classification. Further, this framework requires no labelled data, leaving it very inexpensive. Results show that the proposed approach surpasses the state-of-art approaches by a significant margin.
Zero-shot classification is the task of classifying the test sample into a new class which was not seen during training. This is possible by establishing a relationship between the training and the testing classes using auxiliary information. In the second part of this thesis, a framework is designed that trains using the handcrafted attribute vectors and word vectors but doesn’t require the expensive attribute vectors during test time. More specifically, an intermediate space is learnt between the word vector space and the image feature space using the hand-crafted attribute vectors. Preliminary results on two zero-shot classification datasets show that this is a promising direction to explore.
Image Hashing is the task of mapping images to binary codes such that some notion of user-defined similarity is preserved. The first part of this work focuses on designing a new framework that uses the hash-tags associated with web images to learn the binary codes. Such codes can be used in several applications like Image Retrieval and Image Classification. Further, this framework requires no labelled data, leaving it very inexpensive. Results show that the proposed approach surpasses the state-of-art approaches by a significant margin.
Zero-shot classification is the task of classifying the test sample into a new class which was not seen during training. This is possible by establishing a relationship between the training and the testing classes using auxiliary information. In the second part of this thesis, a framework is designed that trains using the handcrafted attribute vectors and word vectors but doesn’t require the expensive attribute vectors during test time. More specifically, an intermediate space is learnt between the word vector space and the image feature space using the hand-crafted attribute vectors. Preliminary results on two zero-shot classification datasets show that this is a promising direction to explore.
ContributorsGattupalli, Jaya Vijetha (Author) / Li, Baoxin (Thesis advisor) / Yang, Yezhou (Committee member) / Venkateswara, Hemanth (Committee member) / Arizona State University (Publisher)
Created2019
Description
The ubiquity of single camera systems in society has made improving monocular depth estimation a topic of increasing interest in the broader computer vision community. Inspired by recent work in sparse-to-dense depth estimation, this thesis focuses on sparse patterns generated from feature detection based algorithms as opposed to regular grid sparse patterns used by previous work. This work focuses on using these feature-based sparse patterns to generate additional depth information by interpolating regions between clusters of samples that are in close proximity to each other. These interpolated sparse depths are used to enforce additional constraints on the network’s predictions. In addition to the improved depth prediction performance observed from incorporating the sparse sample information in the network compared to pure RGB-based methods, the experiments show that actively retraining a network on a small number of samples that deviate most from the interpolated sparse depths leads to better depth prediction overall.
This thesis also introduces a new metric, titled Edge, to quantify model performance in regions of an image that show the highest change in ground truth depth values along either the x-axis or the y-axis. Existing metrics in depth estimation like Root Mean Square Error(RMSE) and Mean Absolute Error(MAE) quantify model performance across the entire image and don’t focus on specific regions of an image that are hard to predict. To this end, the proposed Edge metric focuses specifically on these hard to classify regions. The experiments also show that using the Edge metric as a small addition to existing loss functions like L1 loss in current state-of-the-art methods leads to vastly improved performance in these hard to classify regions, while also improving performance across the board in every other metric.
This thesis also introduces a new metric, titled Edge, to quantify model performance in regions of an image that show the highest change in ground truth depth values along either the x-axis or the y-axis. Existing metrics in depth estimation like Root Mean Square Error(RMSE) and Mean Absolute Error(MAE) quantify model performance across the entire image and don’t focus on specific regions of an image that are hard to predict. To this end, the proposed Edge metric focuses specifically on these hard to classify regions. The experiments also show that using the Edge metric as a small addition to existing loss functions like L1 loss in current state-of-the-art methods leads to vastly improved performance in these hard to classify regions, while also improving performance across the board in every other metric.
ContributorsRai, Anshul (Author) / Yang, Yezhou (Thesis advisor) / Zhang, Wenlong (Committee member) / Liang, Jianming (Committee member) / Arizona State University (Publisher)
Created2019
Description
This work solves the problem of incorrect rotations while using handheld devices.Two new methods which improve upon previous works are explored. The first method
uses an infrared camera to capture and detect the user’s face position and orient the
display accordingly. The second method utilizes gyroscopic and accelerometer data
as input to a machine learning model to classify correct and incorrect rotations.
Experiments show that these new methods achieve an overall success rate of 67%
for the first and 92% for the second which reaches a new high for this performance
category. The paper also discusses logistical and legal reasons for implementing this
feature into an end-user product from a business perspective. Lastly, the monetary
incentive behind a feature like irRotate in a consumer device and explore related
patents is discussed.
uses an infrared camera to capture and detect the user’s face position and orient the
display accordingly. The second method utilizes gyroscopic and accelerometer data
as input to a machine learning model to classify correct and incorrect rotations.
Experiments show that these new methods achieve an overall success rate of 67%
for the first and 92% for the second which reaches a new high for this performance
category. The paper also discusses logistical and legal reasons for implementing this
feature into an end-user product from a business perspective. Lastly, the monetary
incentive behind a feature like irRotate in a consumer device and explore related
patents is discussed.
ContributorsTallman, Riley (Author) / Yang, Yezhou (Thesis advisor) / Liang, Jianming (Committee member) / Chen, Yinong (Committee member) / Arizona State University (Publisher)
Created2020
Description
The need for incorporating game engines into robotics tools becomes increasingly crucial as their graphics continue to become more photorealistic. This thesis presents a simulation framework, referred to as OpenUAV, that addresses cloud simulation and photorealism challenges in academic and research goals. In this work, OpenUAV is used to create a simulation of an autonomous underwater vehicle (AUV) closely following a moving autonomous surface vehicle (ASV) in an underwater coral reef environment. It incorporates the Unity3D game engine and the robotics software Gazebo to take advantage of Unity3D's perception and Gazebo's physics simulation. The software is developed as a containerized solution that is deployable on cloud and on-premise systems.
This method of utilizing Gazebo's physics and Unity3D perception is evaluated for a team of marine vehicles (an AUV and an ASV) in a coral reef environment. A coordinated navigation and localization module is presented that allows the AUV to follow the path of the ASV. A fiducial marker underneath the ASV facilitates pose estimation of the AUV, and the pose estimates are filtered using the known dynamical system model of both vehicles for better localization. This thesis also investigates different fiducial markers and their detection rates in this Unity3D underwater environment. The limitations and capabilities of this Unity3D perception and Gazebo physics approach are examined.
This method of utilizing Gazebo's physics and Unity3D perception is evaluated for a team of marine vehicles (an AUV and an ASV) in a coral reef environment. A coordinated navigation and localization module is presented that allows the AUV to follow the path of the ASV. A fiducial marker underneath the ASV facilitates pose estimation of the AUV, and the pose estimates are filtered using the known dynamical system model of both vehicles for better localization. This thesis also investigates different fiducial markers and their detection rates in this Unity3D underwater environment. The limitations and capabilities of this Unity3D perception and Gazebo physics approach are examined.
ContributorsAnand, Harish (Author) / Das, Jnaneshwar (Thesis advisor) / Yang, Yezhou (Committee member) / Berman, Spring M (Committee member) / Arizona State University (Publisher)
Created2020
Description
Many real-world planning problems can be modeled as Markov Decision Processes (MDPs) which provide a framework for handling uncertainty in outcomes of action executions. A solution to such a planning problem is a policy that handles possible contingencies that could arise during execution. MDP solvers typically construct policies for a problem instance without re-using information from previously solved instances. Research in generalized planning has demonstrated the utility of constructing algorithm-like plans that reuse such information. However, using such techniques in an MDP setting has not been adequately explored.
This thesis presents a novel approach for learning generalized partial policies that can be used to solve problems with different object names and/or object quantities using very few example policies for learning. This approach uses abstraction for state representation, which allows the identification of patterns in solutions such as loops that are agnostic to problem-specific properties. This thesis also presents some theoretical results related to the uniqueness and succinctness of the policies computed using such a representation. The presented algorithm can be used as fast, yet greedy and incomplete method for policy computation while falling back to a complete policy search algorithm when needed. Extensive empirical evaluation on discrete MDP benchmarks shows that this approach generalizes effectively and is often able to solve problems much faster than existing state-of-art discrete MDP solvers. Finally, the practical applicability of this approach is demonstrated by incorporating it in an anytime stochastic task and motion planning framework to successfully construct free-standing tower structures using Keva planks.
This thesis presents a novel approach for learning generalized partial policies that can be used to solve problems with different object names and/or object quantities using very few example policies for learning. This approach uses abstraction for state representation, which allows the identification of patterns in solutions such as loops that are agnostic to problem-specific properties. This thesis also presents some theoretical results related to the uniqueness and succinctness of the policies computed using such a representation. The presented algorithm can be used as fast, yet greedy and incomplete method for policy computation while falling back to a complete policy search algorithm when needed. Extensive empirical evaluation on discrete MDP benchmarks shows that this approach generalizes effectively and is often able to solve problems much faster than existing state-of-art discrete MDP solvers. Finally, the practical applicability of this approach is demonstrated by incorporating it in an anytime stochastic task and motion planning framework to successfully construct free-standing tower structures using Keva planks.
ContributorsKala Vasudevan, Deepak (Author) / Srivastava, Siddharth (Thesis advisor) / Zhang, Yu (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2020
Description
Question answering is a challenging problem and a long term goal of Artificial Intelligence. There are many approaches proposed to solve this problem, including end to end machine learning systems, Information Retrieval based approaches and Textual Entailment. Despite being popular, these methods find difficulty in solving problems that require multi level reasoning and combining independent pieces of knowledge, for example, a question like "What adaptation is necessary in intertidal ecosystems but not in reef ecosystems?'', requires the system to consider qualities, behaviour or features of an organism living in an intertidal ecosystem and compare with that of an organism in a reef ecosystem to find the answer. The proposed solution is to solve a genre of questions, which is questions based on "Adaptation, Variation and Behavior in Organisms", where there are various different independent sets of knowledge required for answering questions along with reasoning. This method is implemented using Answer Set Programming and Natural Language Inference (which is based on machine learning ) for finding which of the given options is more probable to be the answer by matching it with the knowledge base. To evaluate this approach, a dataset of questions and a knowledge base in the domain of "Adaptation, Variation and Behavior in Organisms" is created.
ContributorsBatni, Vaishnavi (Author) / Baral, Chitta (Thesis advisor) / Anwar, Saadat (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2019
Description
Artificial general intelligence consists of many components, one of which is Natural Language Understanding (NLU). One of the applications of NLU is Reading Comprehension where it is expected that a system understand all aspects of a text. Further, understanding natural procedure-describing text that deals with existence of entities and effects of actions on these entities while doing reasoning and inference at the same time is a particularly difficult task. A recent natural language dataset by the Allen Institute of Artificial Intelligence, ProPara, attempted to address the challenges to determine entity existence and entity tracking in natural text.
As part of this work, an attempt is made to address the ProPara challenge. The Knowledge Representation and Reasoning (KRR) community has developed effective techniques for modeling and reasoning about actions and similar techniques are used in this work. A system consisting of Inductive Logic Programming (ILP) and Answer Set Programming (ASP) is used to address the challenge and achieves close to state-of-the-art results and provides an explainable model. An existing semantic role label parser is modified and used to parse the dataset.
On analysis of the learnt model, it was found that some of the rules were not generic enough. To overcome the issue, the Proposition Bank dataset is then used to add knowledge in an attempt to generalize the ILP learnt rules to possibly improve the results.
As part of this work, an attempt is made to address the ProPara challenge. The Knowledge Representation and Reasoning (KRR) community has developed effective techniques for modeling and reasoning about actions and similar techniques are used in this work. A system consisting of Inductive Logic Programming (ILP) and Answer Set Programming (ASP) is used to address the challenge and achieves close to state-of-the-art results and provides an explainable model. An existing semantic role label parser is modified and used to parse the dataset.
On analysis of the learnt model, it was found that some of the rules were not generic enough. To overcome the issue, the Proposition Bank dataset is then used to add knowledge in an attempt to generalize the ILP learnt rules to possibly improve the results.
ContributorsBhattacharjee, Aurgho (Author) / Baral, Chitta (Thesis advisor) / Yang, Yezhou (Committee member) / Anwar, Saadat (Committee member) / Arizona State University (Publisher)
Created2019
Description
Traditional Reinforcement Learning (RL) assumes to learn policies with respect to reward available from the environment but sometimes learning in a complex domain requires wisdom which comes from a wide range of experience. In behavior based robotics, it is observed that a complex behavior can be described by a combination of simpler behaviors. It is tempting to apply similar idea such that simpler behaviors can be combined in a meaningful way to tailor the complex combination. Such an approach would enable faster learning and modular design of behaviors. Complex behaviors can be combined with other behaviors to create even more advanced behaviors resulting in a rich set of possibilities. Similar to RL, combined behavior can keep evolving by interacting with the environment. The requirement of this method is to specify a reasonable set of simple behaviors. In this research, I present an algorithm that aims at combining behavior such that the resulting behavior has characteristics of each individual behavior. This approach has been inspired by behavior based robotics, such as the subsumption architecture and motor schema-based design. The combination algorithm outputs n weights to combine behaviors linearly. The weights are state dependent and change dynamically at every step in an episode. This idea is tested on discrete and continuous environments like OpenAI’s “Lunar Lander” and “Biped Walker”. Results are compared with related domains like Multi-objective RL, Hierarchical RL, Transfer learning, and basic RL. It is observed that the combination of behaviors is a novel way of learning which helps the agent achieve required characteristics. A combination is learned for a given state and so the agent is able to learn faster in an efficient manner compared to other similar approaches. Agent beautifully demonstrates characteristics of multiple behaviors which helps the agent to learn and adapt to the environment. Future directions are also suggested as possible extensions to this research.
ContributorsVora, Kevin Jatin (Author) / Zhang, Yu (Thesis advisor) / Yang, Yezhou (Committee member) / Praharaj, Sarbeswar (Committee member) / Arizona State University (Publisher)
Created2021
Description
Generative models in various domain such as images, speeches, and videos are beingdeveloped actively over the last decades and recent deep generative models are now
capable of synthesizing multimedia contents are difficult to be distinguishable from
authentic contents. Such capabilities cause concerns such as malicious impersonation,
Intellectual property theft(IP theft) and copyright infringement.
One method to solve these threats is to embedded attributable watermarking in
synthesized contents so that user can identify the user-end models where the contents
are generated from. This paper investigates a solution for model attribution, i.e., the
classification of synthetic contents by their source models via watermarks embedded
in the contents. Existing studies showed the feasibility of model attribution in the
image domain and tradeoff between attribution accuracy and generation quality under
the various adversarial attacks but not in speech domain.
This work discuss the feasibility of model attribution in different domain and
algorithmic improvements for generating user-end speech models that empirically
achieve high accuracy of attribution while maintaining high generation quality. Lastly,
several experiments are conducted show the tradeoff between attributability and
generation quality under a variety of attacks on generated speech signals attempting
to remove the watermarks.
ContributorsCho, Yongbaek (Author) / Yang, Yezhou (Thesis advisor) / Ren, Yi (Committee member) / Trieu, Ni (Committee member) / Arizona State University (Publisher)
Created2021
Description
In recent years, there has been significant progress in deep learning and computer vision, with many models proposed that have achieved state-of-art results on various image recognition tasks. However, to explore the full potential of the advances in this field, there is an urgent need to push the processing of deep networks from the cloud to edge devices. Unfortunately, many deep learning models cannot be efficiently implemented on edge devices as these devices are severely resource-constrained. In this thesis, I present QU-Net, a lightweight binary segmentation model based on the U-Net architecture. Traditionally, neural networks consider the entire image to be significant. However, in real-world scenarios, many regions in an image do not contain any objects of significance. These regions can be removed from the original input allowing a network to focus on the relevant regions and thus reduce computational costs. QU-Net proposes the salient regions (binary mask) that the deeper models can use as the input. Experiments show that QU-Net helped achieve a computational reduction of 25% on the Microsoft Common Objects in Context (MS COCO) dataset and 57% on the Cityscapes dataset. Moreover, QU-Net is a generalizable model that outperforms other similar works, such as Dynamic Convolutions.
ContributorsSanthosh Kumar Varma, Rahul (Author) / Yang, Yezhou (Thesis advisor) / Fan, Deliang (Committee member) / Yang, Yingzhen (Committee member) / Arizona State University (Publisher)
Created2021