Search Constraints

Start Over
Filtering by: Creator Hadley, Adam S. Remove constraint Creator: Hadley, Adam S. Advisor Li, Fuxin Remove constraint Advisor: Li, Fuxin

Search Results

  • 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
    Full Text:
    ) Pixel-level probability Sn,mip,jp ; (b) Voronoi-based probability S n,m p for the example image in

  • 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
    Full Text:
    into the parameters of the corresponding layer in the target network. The discriminator D forces Q(s|z

  • Deep Segmentation in Plant Phenomics

    Creator:
    Kaur, Damanpreet
    Abstract:
    The abilities of plant biologists to characterize the genetic basis of physiological traits are limited by their abilities to obtain quantitative data representing precise details of trait variation and mainly to collect this data on a high-throughput scale at low cost. Deep learning-based methods have demonstrated unprecedented potential to automate...
    Resource Type:
    Masters Thesis
    Full Text:
    the Adam Optimizer. We choose the initial learning rate of 1e-4 and use the bootstrapped cross

  • Deep Convolutional Network on Point Clouds for 3D Scene Understanding

    Creator:
    Wu, Wenxuan
    Abstract:
    As one of the most popular data types, the point cloud is widely used in various appli- cations, including computer vision, computer graphics and robotics. The capability to directly measure 3D point clouds is invaluable in those applications as depth information could remove a lot of the segmentation ambiguities in...
    Resource Type:
    Dissertation

  • 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

  • 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:
    HyperGAN architecture. The mixer transforms s ∼ S into latent codes {q1, . . . , qN}. The generators each

  • Flex-shape convolution and an interactive image segmentation system

    Creator:
    Zhou, Zheng
    Abstract:
    Semantic image segmentation is a relatively difficult task in computer vision. With the advent of deep learning, semantic image segmentation is increasingly of interest for researchers because of the excellent predictions from Convolutional Neural Network (CNN). However, CNNs have proven to struggle with obtaining global context of image due to...
    Resource Type:
    Masters Thesis
    Full Text:
    locates at the same position. Given pooling filter size p× p and stride s, the final output volume size

  • Towards Annotation-Efficient Video Representation Learning

    Creator:
    Patravali, Jay Sanjay
    Abstract:
    Labeling videos is costly, time-consuming and tedious. These costs can escalate in applications such as medical diagnosis or autonomous driving where we need domain expertise for annotation. Few-shot action recognition aims to solve this problem by annotation-efficient learning mechanisms. This thesis presents MetaUVFS as the first Unsupervised Meta-learning algorithm for...
    Resource Type:
    Masters Thesis
    Full Text:
    generate s support augmentations for sampled videos and compute adapted parameters with gradient descent

  • Leveraging Structures of the Data in Deep Learning

    Creator:
    Li, Xingyi
    Abstract:
    The performance of deep learning frameworks could be significantly improved through considering the particular underlying structures for each dataset. In this thesis, I summarize our three work about boosting the performance of deep learning models through leveraging structures of the data. In the first work, we theoretically justify that, for...
    Resource Type:
    Dissertation

  • Visual object discovery and understanding

    Creator:
    Yuan, Jialin
    Abstract:
    Learning to recognize objects is a fundamental and essential step in human perception and understanding of the world. Accordingly, research of object discovery across diverse modalities plays a pivotal role in the context of computer vision. This field not only contributes significantly to enhancing our understanding of visual information but...
    Resource Type:
    Dissertation