MLSP-L6.3
UAMIX-MAE: EFFICIENT TUNING OF PRETRAINED AUDIO TRANSFORMERS WITH UNSUPERVISED AUDIO MIXTURES
Afrina Tabassum, Virginia Tech, United States of America; Dung Tran, Trung Dang, Microsoft, United States of America; Ismini Lourentzou, Virginia Tech, United States of America; Kazuhito Koishida, Microsoft, United States of America
Session:
MLSP-L6: Self-Supervised and Semi-Supervised Learning I Lecture
Track:
Machine Learning for Signal Processing
Location:
Room 102
Presentation Time:
Wed, 17 Apr, 09:00 - 09:20 (UTC +9)
Session Co-Chairs:
Justin Dauwels, Delft University of Technology and Leibny Paola Garcia, Johns Hopkins University
Session MLSP-L6
MLSP-L6.1: J-MAE: JIGSAW MEETS MASKED AUTOENCODERS IN X-RAY SECURITY INSPECTION
Weichen Xu, Jian Cao, Tianhao Fu, Peking University, China; Awen Bai, Beihang University, China; Ruilong Ren, Zicong Hu, Xixin Cao, Xing Zhang, Peking University, China
MLSP-L6.2: Adaptive Multi-View Joint Contrastive Learning on Graphs
Long Chen, Qianqian Ren, Zilong Li, Hui Xu, Heilongjiang University, China
MLSP-L6.3: UAMIX-MAE: EFFICIENT TUNING OF PRETRAINED AUDIO TRANSFORMERS WITH UNSUPERVISED AUDIO MIXTURES
Afrina Tabassum, Virginia Tech, United States of America; Dung Tran, Trung Dang, Microsoft, United States of America; Ismini Lourentzou, Virginia Tech, United States of America; Kazuhito Koishida, Microsoft, United States of America
MLSP-L6.4: CONTRASTIVE LEARNING FOR REGRESSION ON HYPERSPECTRAL DATA
Mohamad DHAINI, Maxime Berar, Paul Honeine, University Rouen Normandie, France; Antonin Van Exem, Tellux Company, France
MLSP-L6.5: Credible Teacher for Semi-Supervised Object Detection in Open Scene
Jingyu Zhuang, Kuo Wang, Liang Lin, Guanbin Li, Sun Yat-sen University, China
MLSP-L6.6: DMT: Comprehensive Distillation with Multiple Self-supervised Teachers
Yuang Liu, East China Normal University, China; Jing Wang, Qiang Zhou, Fan Wang, Alibaba Group, China; Jun Wang, Wei Zhang, East China Normal University, China
Contacts