Effective image synthesis for effective deep neural network training
State-of-the-art deep neural networks (DNNs) necessitate a significant number of images to achieve accurate and robust models. However, gathering a large amount of images remains the prevailing approach, which proves expensive, time-consuming, and challenging to scale across different tasks and d...
Saved in:
Main Author: | Cui, Kaiwen |
---|---|
Other Authors: | Lu Shijian |
Format: | Thesis-Doctor of Philosophy |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/174934 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Deep graph neural networks for link prediction
by: Zheng, MingXi
Published: (2024) -
Study of fine-tuning the pre-trained deep convolutional neural networks for image recognition
by: Nur Azila Azman
Published: (2020) -
Learning deep networks for image classification
by: Zhou, Yixuan
Published: (2024) -
Learning deep networks for image segmentation
by: Akash, T
Published: (2024) -
Effects of incremental training on watermarked neural networks
by: Heng, Chuan Song
Published: (2023)