Premium
Learning algorithm with noisy labels for video frame classification
Author(s) -
Lee Junggi,
Kong Kyeongbo,
Song WooJin
Publication year - 2020
Publication title -
journal of the society for information display
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.578
H-Index - 52
eISSN - 1938-3657
pISSN - 1071-0922
DOI - 10.1002/jsid.959
Subject(s) - computer science , frame (networking) , artificial intelligence , pattern recognition (psychology) , computer vision , algorithm , telecommunications
In this paper, we propose Recycling+, an algorithm that uses temporal information for video frame classification with noisy label. With the proposed algorithm, the network can be trained robustly through not only clean samples with original labels but also noisy samples with corrected labels obtained by temporal average predictions.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom