Index Catalog // ScholarsArchive@OSU

Open Set Learning with Counterfactual Images

Creator:: Neal, Lawrence W.
Abstract:: In open set recognition, a classifier must label instances of known classes while detecting instances of unknown classes not encountered during training. To detect unknown classes while still generalizing to new instances of existing classes, this thesis introduces a dataset augmentation technique called counterfactual image generation. This approach, based on...
Resource Type:: Masters Thesis
Full Text:: the IEEE conference on computer vision and pattern recognition, pages 1563–1572, 2016. [3] David

Individual Fairness Optimization in Machine Learning with Minimax Loss and an Abstain Option

Creator:: Behnoudfar, Ali
Abstract:: In this thesis, a new learning algorithm is introduced that is targeted towards individual fairness. In order to be individually fair, mispredictions need to be avoided as each such prediction means the learning algorithm was unfair towards some individual. Therefore, achieving individual fairness implies having a perfect classifier, which is...
Resource Type:: Masters Thesis
Full Text:: , New York, NY, USA, 2018. Association for Computing Machinery. [5] Jose Blanchet and Karthyek R. A

Methods for Detection and Recovery of Out-of-Distribution Examples

Creator:: Ratzlaff, Neale J.
Abstract:: Deep neural networks currently comprise the backbone of many applications where safety is a critical concern, for example: autonomous driving and medical diagnostics. Unfortunately these systems currently fail to detect out-of-distribution (OOD) inputs and can be prone to making dangerous errors when exposed to them. In addition, these same systems...
Resource Type:: Masters Thesis
Full Text:: ”. David Lyndsay. The Monarchie (1554) TABLE OF CONTENTS Page 1 Introduction 1 1.1 Overview

Uncertainty in Deep Learning with Implicit Neural Networks

Creator:: Ratzlaff, Neale
Abstract:: The ability to extract uncertainties from predictions is crucial for the adoption of deep learning systems to safety-critical applications. Uncertainty estimates can be used as a failure signal, which is necessary for automating complex tasks where safety is a concern. Furthermore, current deep learning systems do not provide uncertainty estimates,...
Resource Type:: Dissertation

Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression

Creator:: Wang, Xinyao
Abstract:: Heatmap regression has became one of the mainstream approaches to localize facial landmarks. As Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) are becoming popular in solving computer vision tasks, extensive research has been done on these architectures. However, the loss function for heatmap regression is rarely studied. In...
Resource Type:: Masters Thesis

Toward Disentangling the Activations of the Deep Networks via Low-dimensional Embedding and Non-negative Factorization

Creator:: Khorram, Saeed
Abstract:: In this thesis, we introduce a novel Explanation Neural Network (XNN) to explain the predictions made by a deep network. The XNN works by embedding a high-dimensional activation vector of a deep network layer non-linearly into a low-dimensional explanation space while retaining faithfulness i.e., the original deep learning predictions can...
Resource Type:: Masters Thesis

Video Analysis : Techniques for Semi-Supervised Video Object Instance Segmentation and Tracking-by-Detection in the Wild

Creator:: Firl, Alrik K.
Abstract:: This thesis consists of two major components. The first part is concerned with video object instance segmentation (VOS), which is the task of assigning per-pixel labels perframe of a video sequence to indicate foreground object instance membership, given the first frame ground truth mask. VOS has myriad applications, from video...
Resource Type:: Masters Thesis

Deep Perception Without a Camera: Enabling 3D Reconstruction and Object Recognition using Lidar and Sonar Sensing

Creator:: DeBortoli, Robert A.
Abstract:: Deep learning has recently revolutionized robot perception in many canonical robotic applications, such as autonomous driving. However, a similar transformation has yet to occur in more harsh environments including underwater and underground. This is due in part to the difficulty in deploying robots in these environments, which lack large real...
Resource Type:: Dissertation

Generative Models Meet Explainable AI and Long-Tail Learning: from Attribution Maps to Image Synthesis

Creator:: Khorram, Saeed
Abstract:: The advancement of artificial intelligence (AI) has led to transformative developments across multiple sectors, fostering innovation and redefining our interactions with technology. As AI matures and becomes integrated into society, it offers numerous opportunities to address global challenges and revolutionize a wide array of human endeavors. These advances are driven...
Resource Type:: Dissertation
Full Text:: , Jay, Lawrence, Chanho, Tim, Robert, Mazen, Ali, Wesley, Skand, Ziwen, Wenxuan, Hung, Amin, David, and

ScholarsArchive@OSU

Open Set Learning with Counterfactual Images

Individual Fairness Optimization in Machine Learning with Minimax Loss and an Abstain Option

Methods for Detection and Recovery of Out-of-Distribution Examples

Uncertainty in Deep Learning with Implicit Neural Networks

Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression

Toward Disentangling the Activations of the Deep Networks via Low-dimensional Embedding and Non-negative Factorization

Video Analysis : Techniques for Semi-Supervised Video Object Instance Segmentation and Tracking-by-Detection in the Wild

Deep Perception Without a Camera: Enabling 3D Reconstruction and Object Recognition using Lidar and Sonar Sensing

Generative Models Meet Explainable AI and Long-Tail Learning: from Attribution Maps to Image Synthesis

Limit your search

Academic Affiliation

Advisor

Commencement Year

Committee Member

Creator

Contributor

Date

Decade

Degree Field

Degree Level

Degree Name

Language

License

Peer Reviewed

Resource Type

Rights Statement

Subject

Search Constraints

Search Results

Limit your search