Few-shot vision recognition and generation for the open-world

Deep Neural Networks (DNNs) have achieved remarkable success across various computer vision tasks, but their reliance on extensive labeled datasets limits their applicability in data-scarce scenarios. Few-shot learning offers a promising solution by enabling models to learn from minimal data, yet tr...

Full description

Saved in:
Bibliographic Details
Main Author: Song, Nan
Other Authors: Lin Guosheng
Format: Thesis-Doctor of Philosophy
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/181293
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English

Similar Items