Search Constraints

Start Over
Filtering by: Creator Wang, Wei Remove constraint Creator: Wang, Wei Committee Member Fern, Alan Remove constraint Committee Member: Fern, Alan

Search Results

  • Image features and learning algorithms for biological, generic and social object recognition

    Creator:
    Zhang, Wei
    Abstract:
    Automated recognition of object categories in images is a critical step for many real-world computer vision applications. Interest region detectors and region descriptors have been widely employed to tackle the variability of objects in pose, scale, lighting, texture, color, and so on. Different types of object recognition problems usually require...
    Resource Type:
    Dissertation
    Full Text:
    AN ABSTRACT OF THE DISSERTATION OF Wei Zhang for the degree of Doctor of Philosophy in Electrical

  • 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:
    more interesting topics. I am very grateful to my mentors and co-workers during the internships: Wei

  • 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:
    − 10. Final test accuracy: ”Stochastic Block ADMM”: 90.39%, ”Wang et al.”:84.67% (averaged over 5 runs

  • Robust and Efficient Classification of Videos in the Wild

    Creator:
    Mahasseni, Behrooz
    Abstract:
    Recognizing human actions in videos is a long-standing problem in computer vision with a wide range of applications including video surveillance, content retrieval, and sports analysis. This thesis focuses on addressing efficiency and robustness of video classification in unconstrained real-world settings. The thesis work can be broadly divided into four...
    Resource Type:
    Dissertation

  • Fine-Grained Object Recognition Under Limited Training Data

    Creator:
    Lam, Michael Q.
    Abstract:
    This dissertation addresses object recognition in challenging settings, where distinct object classes are visually very similar (e.g., species of birds and insects) and/or access to training examples of object classes is limited (e.g., due to the associated high costs of data annotation). In this dissertation, we present a variety of...
    Resource Type:
    Dissertation
    Full Text:
    have been used in vision, in- cluding Dual Decomposition [84], Graph-Cuts [13], Swendsen-Wang (SW) cut

  • 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:
    aspect of my research ability. I also extend my thanks to the excellent researchers Wei Xu, Haonan Yu

  • Decentralized Multi-Robot Exploration with Sparse Communication through Deep Imitation Learning

    Creator:
    Senewiratne, Yomal K.
    Abstract:
    We present a method for decentralized, multi-robot exploration in adverse environments where communication is minimal. A key conceptual feature of our method is enabling implicit coordination between robots by training a Convolutional Neural Network (CNN) as a heuristic for planning using Monte Carlo Tree Search (MCTS). Our method consists of...
    Resource Type:
    Masters Thesis

  • Incorporating labeled features into image classification using generalized expectation

    Creator:
    Moore, Travis
    Abstract:
    Image classification is a difficult problem, often requiring large training sets to get satisfactory results. However this is a task that humans perform very well, and incorporating user feedback into these learning algorithms could help reduce the dependency on large amounts of labeled training data. This process has already been...
    Resource Type:
    Masters Thesis

  • A Deep Action Segmentation and Its Explanation with a Dictionary of Meaningful Attention Maps

    Creator:
    Trigkakis, Dimitrios
    Abstract:
    This thesis addresses the problem of temporal action segmentation in videos, where the goal is to label every video frame with the appropriate action class present. We focus on the domain of NFL football videos, where action classes represent common football play types. For action segmentation, we use a temporal...
    Resource Type:
    Masters Thesis

  • Characterizing and Addressing Dataset Shift with Deep Learning

    Creator:
    Olson, Matthew L.
    Abstract:
    This dissertation delves into understanding, characterizing, and addressing dataset shift in deep learning, a pervasive issue for deployed machine learning systems. Integral aspects of the problem are examined: We start with the use of counterfactual explanations in order to characterize the behavior of deep reinforcement learning agents in visual input...
    Resource Type:
    Dissertation