Extended T: Learning With Mixed Closed-Set and Open-Set Labels

Xia, XB; Han, B; Wang, NN; Deng, JK; Li, JT; Mao, YN; Liu, TL

Wang, NN (通讯作者),Xidian Univ, Sch Telecommun Engn, State Key Lab Integrated Serv Net works, Xian 710071, Shaanxi, Peoples R China.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023; 45 (3): 3047

Abstract

The noise transition matrix T, reflecting the probabilities that true labels flip into noisy ones, is of vital importance to model label noise and bui......

Full Text Link