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"”.
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …