MLSP-P32: Deep Learning Training Methods III
Fri, 19 Apr, 08:20 - 10:20 (UTC +9)
Location: Poster Zone 2A
Session Type: Poster
Session Chair: Qing Liu, CMVS, University of Oulu
Track: Machine Learning for Signal Processing
Click the to view the manuscript on IEEE Xplore Open Preview
 

MLSP-P32.1: LIPSCHITZ-CONSTRAINED CONVOLUTIONAL LAYERS USING CONVEX PROJECTION

Bhartendu Kumar, Kunal Chaudhury, Indian Institute of Science, India
 

MLSP-P32.2: CROSS-IMAGE DISTILLATION FOR SEMI-SUPERVISED SEMANTIC SEGMENTATION

Nan Zhang, Fan Xiao, Junlin Hou, Rui-Wei Zhao, Fudan University, China; Xiaobo Zhang, Children’s Hospital of Fudan University, National Children’s Medical Center, China; Rui Feng, Fudan University, China
 

MLSP-P32.3: FROM GAME THEORY TO VISUAL RECOGNITION: ADVANCING DNN ROBUSTNESS

Zhendong Liu, Wenyu Jiang, Ming Guo, Chongjun Wang, Nanjing University, China
 

MLSP-P32.5: The power of few: accelerating and enhancing data reweighting with coreset selection

Mohammad Jafari, Sharif University of Technology, Iran (Islamic Republic of); Yimeng Zhang, Yihua Zhang, Sijia Liu, Michigan State University, United States of America
 

MLSP-P32.6: AutoSGM: A Unified Lowpass Regularization Framework for Accelerated Learning

Oluwasegun Somefun, Stefan Lee, V John Mathews, Oregon State University, United States of America
 

MLSP-P32.7: REVISITING THE EQUIVALENCE OF IN-CONTEXT LEARNING AND GRADIENT DESCENT: THE IMPACT OF DATA DISTRIBUTION

Sadegh Mahdavi, Renjie Liao, Christos Thrampoulidis, University of British Columbia, Canada
 

MLSP-P32.9: Neural Network Training Strategy to Enhance Anomaly Detection Performance: A Perspective on Reconstruction Loss Amplification

YeongHyeon Park, Sungho Kang, Sungkyunkwan University, Korea, Republic of; Myung Jin Kim, SK Planet Co., Ltd., Korea, Republic of; Hyeonho Jeong, Hyunkyu Park, Sungkyunkwan University, Korea, Republic of; Hyeong Seok Kim, SK Planet Co., Ltd., Korea, Republic of; Juneho Yi, Sungkyunkwan University, Korea, Republic of
 

MLSP-P32.10: Segmented Error Minimisation (SEMI) for Robust Training of Deep Learning Models with Non-linear Shifts in Reference Data

Harry Davies, Yuyang Miao, Amir Nassibi, Imperial College London, United Kingdom of Great Britain and Northern Ireland; Morteza Khaleghimeybodi, Meta Reality Labs, United States of America; Danilo Mandic, Imperial College London, United Kingdom of Great Britain and Northern Ireland
 

MLSP-P32.11: COPHTC: CONTRASTIVE LEARNING WITH PROMPT TUNING FOR HIERARCHICAL TEXT CLASSIFICATION

Fuhan Cai, Zhongqiang Zhang, Duo Liu, Xiangzhong Fang, Shanghai Jiao Tong University, China