Search Constraints

Start Over
Filtering by: Creator Lam, Adam Q. Remove constraint Creator: Lam, Adam Q. 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:
    explanation space to be orthogonal; (c) The log penalty function log(1 + q · r2) when q = 1; (d) The log

  • 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

  • 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:
    Scale, including Chiao-Lun Cheng, Adrian Lam, Daniel Havir, and Felix Lau, for their teamwork and

  • 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
    Full Text:
    cloud Q. Then, we ag- gregate the cost from patch NP (pc) in the point cloud P . (b) Cost Volume Layer

  • 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:
    discriminator forces Q(q|s) to be well-distributed and close to P . . . . . 14 2.2 Results of HyperGAN on the

  • 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:
    linear mappings, key-head K : RD → Rdk , value- head V : RD → Rdv and query-head Q : RD → Rdk for this

  • 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

  • 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:
    Counterfactual Image Generation In logic, a conditional statement p→ q is true if the antecedent statement p

  • 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

  • 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:
    as Adagrad[6], Adam[14], Adadelta[32], etc. But most of them are gradient-based learning approaches