IEEE - Institute of Electrical and Electronics Engineers, Inc. - Significance of Softmax-based Features in Comparison to Distance Metric Learning-based Features

Author(s): Shota Horiguchi ; Daiki Ikami ; Kiyoharu Aizawa
Sponsor(s): IEEE Computer Society
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Volume: PP
Page(s): 1
ISSN (CD): 2160-9292
ISSN (Electronic): 1939-3539
ISSN (Paper): 0162-8828
DOI: 10.1109/TPAMI.2019.2911075
Regular:

End-to-end distance metric learning (DML) has been applied to obtain features useful in many computer vision tasks. However, these DML studies have not provided equitable comparisons between... View More

Advertisement