A comparative study of data augmentation techniques for image classification: generative models vs. classical transformations
Advances in deep convolutional neural networks and efficient parallel processing are showing great promise when applied to image classification, object detection, image restoration and image segmentation. However, deep models require large amounts of annotated training data, which are not always acc...
| Autor principal: | |
|---|---|
| Formato: | masterThesis |
| Idioma: | eng |
| Publicado em: |
2021
|
| Assuntos: | |
| Texto completo: | http://hdl.handle.net/10773/30759 |
| País: | Portugal |
| Oai: | oai:ria.ua.pt:10773/30759 |