TU5.L3.3
HARNESSING FEATURE DISTRIBUTION CONSISTENCY FOR FEDERATED LEARNING WITH NOISY LABELS
Yali Ma, Baoyao Yang, Yanchao Tang, Weide Zhan, Guangdong University of Technology, China; Wenyin Yang, Foshan University, China
Session:
TU5.L3: Machine Learning in Signal Processing 6 Lecture
Track:
[ML] Machine Learning in Signal Processing
Location:
Room 1
Presentation Time:
Tue, 16 Sep, 17:00 - 17:15 Anchorage Time (UTC -8)
Session Chair:
Shan Du, UBC-O
Presentation
Discussion
Resources
No resources available.
Session TU5.L3
TU5.L3.1: Overlooked Factors in Continual Zero-Shot Learning: Inflexible Semantic Prototypes, Simplistic Loss Functions, and SGD Noise
Qingyang Hao, Lei Li, Chun Yuan, Tsinghua University, China
TU5.L3.2: IMPLICIT OBJECT RECOGNITION VIA REINFORCEMENT LEARNING IN OUT-OF-DOMAIN SCENARIOS
Kenji Cari Koga, Rei Kawakami, Institute of Science Tokyo, Japan
TU5.L3.3: HARNESSING FEATURE DISTRIBUTION CONSISTENCY FOR FEDERATED LEARNING WITH NOISY LABELS
Yali Ma, Baoyao Yang, Yanchao Tang, Weide Zhan, Guangdong University of Technology, China; Wenyin Yang, Foshan University, China
TU5.L3.4: ST-GRIT: SPATIO-TEMPORAL GRAPH TRANSFORMER FOR INTERNAL ICE LAYER THICKNESS PREDICTION
Zesheng Liu, Maryam Rahnemoonfar, Lehigh University, United States
TU5.L3.5: FINE-GRAINED SPATIAL-TEMPORAL PERCEPTION FOR GAS LEAK SEGMENTATION
Xinlong Zhao, Shan Du, The University of British Columbia - Okanagan, Canada
TU5.L3.6: When 512×512 Is Not Enough: Local Degradation-Aware Multi-Diffusion for Extreme Image Super-Resolution
Brian Moser, Stanislav Frolov, Tobias Nauen, Federico Raue, Andreas Dengel, German Research Center for Artificial Intelligence, Germany
Contacts