Please use this identifier to cite or link to this item:
|Title:||A Study on Angular Softmax||Authors:||Ul Rahman, Jamshaid||Orientador:||Chen, Qing
|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||URI:||http://hdl.handle.net/10316/95693||Rights:||openAccess|
|Appears in Collections:||UC - Reconhecimento de graus e diplomas estrangeiros|
Show full item record
checked on Sep 10, 2021
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.