Learning algorithm with noisy labels for video frame classification

被引：0

作者：

Lee, Junggi ^{[1
]}

Kong, Kyeongbo ^{[1
]}

Song, Woo-Jin ^{[1
]}

机构：

[1] Pohang Univ Sci & Technol, Dept Elect Engn, San 31, Pohang 37673, South Korea

来源：

JOURNAL OF THE SOCIETY FOR INFORMATION DISPLAY | 2020年 / 28卷 / 12期

关键词：

Deep learning; noisy label; semisupervised learning; temporal information; video frame classification; MOTION-ESTIMATION;

D O I：

10.1002/jsid.959

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

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.

引用

页码：997 / 1002

页数：6

共 50 条

[21] Learning From Noisy Labels With Deep Neural Networks: A Survey
Song, Hwanjun
Kim, Minseok
Park, Dongmin
Shin, Yooju
Lee, Jae-Gil
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (11) : 8135 - 8153
[22] Learning From Noisy Labels via Dynamic Loss Thresholding
Yang, Hao
Jin, You-Zhi
Li, Zi-Yin
Wang, Deng-Bao
Geng, Xin
Zhang, Min-Ling
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2024, 36 (11) : 6503 - 6516
[23] ConfidentMix: Confidence-Guided Mixup for Learning With Noisy Labels
Higashimoto, Ryota
Yoshida, Soh
Muneyasu, Mitsuji
IEEE ACCESS, 2024, 12 : 58519 - 58531
[24] Robust Learning by Self-Transition for Handling Noisy Labels
Song, Hwanjun
Kim, Minseok
Park, Dongmin
Shin, Yooju
Lee, Jae-Gil
KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2021, : 1490 - 1500
[25] A Recursive Ensemble Learning Approach With Noisy Labels or Unlabeled Data
Wang, Yuchen
Yang, Yang
Liu, Yun-Xia
Bharath, Anil Anthony
IEEE ACCESS, 2019, 7 : 36459 - 36470
[26] A Convergence Path to Deep Learning on Noisy Labels
Liu, Defu
Tsang, Ivor W.
Yang, Guowu
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (04) : 5170 - 5182
[27] Penalty based robust learning with noisy labels
Kong, Kyeongbo
Lee, Junggi
Kwak, Youngchul
Cho, Young-Rae
Kim, Seong-Eun
Song, Woo-Jin
NEUROCOMPUTING, 2022, 489 : 112 - 127
[28] CORRECTING NOISY LABELS DURING THE CLASSIFICATION OF HYPERSPECTRAL IMAGES
Wei, Qiliang
Fu, Peng
IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 7230 - 7233
[29] Robust Semi-Supervised Classification for Noisy Labels Based on Self-Paced Learning
Gu, Nannan
Fan, Mingyu
Meng, Deyu
IEEE SIGNAL PROCESSING LETTERS, 2016, 23 (12) : 1806 - 1810
[30] Self-Correlation Network With Triple Contrastive Learning for Hyperspectral Image Classification With Noisy Labels
Sarpong, Kwabena
Awrangjeb, Mohammad
Islam, Md. Saiful
Helmy, Islam
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2025, 18 : 7166 - 7188

← 1 2 3 4 5 →