Please use this identifier to cite or link to this item:
Title: A Study on Angular Softmax
Authors: Ul Rahman, Jamshaid
Orientador: Chen, Qing
Yang, Zhouwang
Keywords: Additive Parameter; Angular Margin; Deep Convolutional Neural Networks; Image Recognition; Softmax Loss
Issue Date: May-2020
Place of publication or event: University of Science and Technology of China
Abstract: After the development of Deepface and DeepID methods in 2014, deep learning methods for image recognition has dramatically improved the state-of-the-art performance on Deep Convolutional Neural Networks (DCNNs) and reshaped the research landscape of image processing and data analysis. In spite of rapid improvement in deep learning algorithms, it still has various challenges like adjustment of appropriate loss function and optimization strategy to handle large scale problems in many computer vision applications including Face Recognition (FR) and Handwritten Digit Recognition (HDR). This thesis focus on these challenges and their better solution.
Description: Documentos apresentados no âmbito do reconhecimento de graus e diplomas estrangeiros
Rights: openAccess
Appears in Collections:UC - Reconhecimento de graus e diplomas estrangeiros

Files in This Item:
File Description SizeFormat
Thesis-jamshaid.pdfTese8.72 MBAdobe PDFView/Open
Show full item record

Page view(s)

checked on Sep 10, 2021

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.