Dense Adversarial Transfer Learning Based On Class-invariant

碩士 === 國立中央大學 === 資訊工程學系 === 107 === In recent years, deep neural networks (DNN) have demonstrated their powerful learning ability in image recognition. Such success result requires a large-scale data set as training data. However, acquiring data label in real-life needs high cost. This dilemma cond...

Full description

Bibliographic Details
Main Authors: Ting-Yu Wang, 王莛瑜
Other Authors: Jia-Ching Wang
Format: Others
Language:zh-TW
Published: 2019
Online Access:http://ndltd.ncl.edu.tw/handle/f2cupk