Deep neural network compression for pixel-level vision tasks

• Main Author: He, Wei
• Other Authors: Lam Siew Kei
• Format: Thesis-Master by Research
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• Online Access: https://hdl.handle.net/10356/150076
• Institution: Nanyang Technological University

Deep convolutional neural networks (DCNNs) have demonstrated remarkable performance in many computer vision tasks. In order to achieve this, DCNNs typically require a large number of trainable parameters that are optimized to extract informative features. This often results in over-parameterization...