Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 5 of 5 for “"Orthogonal Regularization"”.

  1. Computation-Efficient Deep Learning Models for Computer Vision and Multimodal Vision-Language Tasks via Network Pruning

    … neural networks, when carefully initialized with orthogonal weights and constrained using orthogonal regularization, can outperform deeper counterparts on specialized classification tasks. Specifically, we show that models tailored to scale-sensitive feature learning can yield competitive …

    sdstate Repository record for Computation-Efficient Deep Learning Models for Computer Vision and Multimodal Vision-Language Tasks via Network Pruning (opens in a new tab)

  2. Exploiting Competition Relationship for Robust Visual Recognition

    … with feature interaction encouraged via an orthogonal regularization over feature importance vectors. Then, an alternating greedy coordinate descent learning algorithm (AGCD) is derived to estimate the model. The algorithm effectively excludes distracting features in a fine-grained level for …

    temple Repository record for Exploiting Competition Relationship for Robust Visual Recognition (opens in a new tab)

  3. DOMAIN ADAPTION FOR UNCONSTRAINED FACE VERIFICATION AND IDENTIFICATION

    … and pose metrics. Specifically, we enforce an orthogonal regularization constraint on the learned projection matrices for the two tasks leading to making the identity metrics for face verification more pose-robust. Extensive experiments are conducted on three challenging unconstrained face …

    maryland Repository record for DOMAIN ADAPTION FOR UNCONSTRAINED FACE VERIFICATION AND IDENTIFICATION (opens in a new tab)

  4. Machine Learning for Environmental Sustainability

    This research proposes a comprehensive approach to address pressing challenges in environmental sustainability, agricultural residue management, using machine learning based approaches. Machine learning (ML) techniques have emerged as powerful tools for addressing environmental sustainability …

    wvu Repository record for Machine Learning for Environmental Sustainability (opens in a new tab)

  5. Multimodal Adversarial Learning

    Deep Convolutional Neural Networks (DCNN) have proven to be an exceptional tool for object recognition, generative modelling, and multi-modal learning in various computer vision applications. However, recent findings have shown that such state-of-the-art models can be easily deceived by inserting …

    wvu Repository record for Multimodal Adversarial Learning (opens in a new tab)