WP2.PC.10
ROBUST FEATURE LEARNING AGAINST NOISY LABEL
Tsung-Ming Tai, Free University of Bozen-Bolzano, Taiwan; Yun-Jie Jhang, National Tsing Hua University, Taiwan; Wen-Jyi Hwang, National Taiwan Normal University, Taiwan
Session:
WP2.PC: Machine Learning Theory and Algorithms for Image Processing II Poster
Track:
Applications of Machine Learning
Location:
Poster Area C
Presentation Time:
Wed, 11 Oct, 16:30 - 18:00 Malaysia Time (UTC +8)
Session Chair:
Michael McCann, Los Alamos National Laboratory
Session WP2.PC
WP2.PC.1: TASK-AGNOSTIC OPEN-SET PROTOTYPE FOR FEW-SHOT OPEN-SET RECOGNITION
Byeonggeun Kim, Amazon Inc., Canada; Jun-Tae Lee, Kyuhong Shim, Simyung Chang, Qualcomm, Korea, Republic of
WP2.PC.2: COST-EFFICIENT MULTI-INSTANCE MULTI-LABEL ACTIVE LEARNING VIA CORRELATION OF FEATURES
Guoliang Su, Zhangquan Wu, Yujia Ye, Southwest University, China; Maoxing Chen, Thundersoft (Chongqing) Automotive Technology Co., Ltd, China; Jun Zhou, Southwest University, China
WP2.PC.3: ADAPTIVE SEMI-SUPERVISED MIXUP WITH IMPLICIT LABEL LEARNING AND SAMPLE RATIO BALANCING
Yulin Su, Liangliang Shi, Shanghai Jiao Tong University, China; Ziming Feng, China Merchants Bank Credit Card Center, China; Pengzhi Chu, Junchi Yan, Shanghai Jiao Tong University, China
WP2.PC.4: TASK-AWARE GRAPH CONVOLUTIONAL NETWORK FOR ACTIVE LEARNING
Yujia Ye, Zhangquan Wu, Guoliang Su, Jun Zhou, College of Computer and Information Science, Southwest University, China
WP2.PC.5: FIGHTING OVER-FITTING WITH QUANTIZATION FOR LEARNING DEEP NEURAL NETWORKS ON NOISY LABELS
Gauthier Tallec, Edouard Yvinec, Sorbonne Université, France; Arnaud Dapogny, Datakalab, France; Kevin Bailly, Sorbonne Université, France
WP2.PC.6: DNC-NET: DUAL-NEIGHBOURHOOD CONSENSUS NETWORK FOR FEATURE MATCHING
Qimin Jiang, Songlin Du, Southeast University, China
WP2.PC.7: OOD ATTACK: GENERATING OVERCONFIDENT OUT-OF-DISTRIBUTION EXAMPLES TO FOOL DEEP NEURAL CLASSIFIERS
Keke Tang, Xujian Cai, Weilong Peng, Shudong Li, Guangzhou University, China; Wenping Wang, Texas A&M University, United States of America
WP2.PC.8: DATA POISONING ATTACK AIMING THE VULNERABILITY OF CONTINUAL LEARNING
Gyojin Han, Jaehyun Choi, Hyeong Gwon Hong, Junmo Kim, Korea Advanced Institute of Science and Technology, Korea, Republic of
WP2.PC.9: LGSQE: LIGHTWEIGHT GENERATED SAMPLE QUALITY EVALUATION
Ganning Zhao, Vasileios Magoulianitis, University of Southern California, United States of America; Suya You, DEVCOM Army Research Laboratory (ARL), United States of America; C.-C. Jay Kuo, University of Southern California, United States of America
WP2.PC.10: ROBUST FEATURE LEARNING AGAINST NOISY LABEL
Tsung-Ming Tai, Free University of Bozen-Bolzano, Taiwan; Yun-Jie Jhang, National Tsing Hua University, Taiwan; Wen-Jyi Hwang, National Taiwan Normal University, Taiwan
WP2.PC.11: Efficient Transfer by Robust Label Selection and Learning with Pseudo-Labels
Wyke Huizinga, Maarten Kruithof, Gertjan Burghouts, Klamer Schutte, TNO, Netherlands
WP2.PC.12: Exploiting the Distortion-Semantic Interaction in Fisheye Data
Kiran Kokilepersaud, Mohit Prabhushankar, Yavuz Yarici, Ghassan AlRegib, Georgia Institute of Technology; Mostafa Parchami, Ford Motor Company
Contacts