MLSP-P68: Unsupervised Learning Methods for Signal Processing
Poster
Thu, 7 May, 16:30 - 18:30
Location: Poster Area 10
Session Type: Poster
Track: Machine Learning for Signal Processing [ML]
Click the to view the manuscript on IEEE Xplore Open Preview

MLSP-P68.1: INVISIBLE BACKDOOR ATTACKS ON SELF-SUPERVISED LEARNING VIA MULTI-CHANNEL ADAPTIVE STEGANOGRAPHY
Wei Shu, Yuanbo Li, Cong Hu, Jiangnan University, China

MLSP-P68.2: DOMAIN DISTILLATION WITH TRANSFORMER FOR UNSUPERVISED DOMAIN ADAPTATION
Eunseop Lee, JoengJun Lee, YoungMin Moon, Research Institute of Industrial Science & Technology, Korea, Republic of

MLSP-P68.3: LFMIM: Low-Frequency Enhanced Reconstruction for Few-Shot SAR-ATR
Ruoxue Li, Shuyuan Yang, XIDIAN UNIVERSITY, China; Hao Hu, Xi'an Jiaotong University, China; Zhixi Feng, Yue Ma, XIDIAN UNIVERSITY, China

MLSP-P68.4: 2 IN 1: A DUAL-PURPOSE APPROACH FOR EO-SAR SHIP DETECTION WITH SOURCE-FREE DOMAIN ADAPTATION
Beomseok Oh, Minsu Kim, Areum Han, Juhyeon Han, Sunok Kim, Korea Aerospace University, Korea, Republic of

MLSP-P68.5: DASE: MAXIMUM ENTROPY DATA SELECTION FOR BALANCED PRETRAINING CORPORA OF LARGE LANGUAGE MODELS
Jie Xiong, Fangxiu Zhong, Jun Wang, Yang Zhang, Southwestern University of Finance and Economics, China; Li Yu, Renmin University of China, China

MLSP-P68.6: Hierarchical Contrastive Learning of Point Clouds Based on P-Norm Pooling
Kuan Liu, Yanmin Zhu, Shanghai Jiao Tong University, China; Ke Wang, Chongqing University, China; Gang Zhou, Hangzhou Innovation Institute, Beihang University, Hangzhou, China, China

MLSP-P68.7: ETUDE: PIANO COVER GENERATION WITH A THREE-STAGE APPROACH — EXTRACT, STRUCTURALIZE, AND DECODE
Tse-Yang Chen, Yuh-Jzer Joung, National Taiwan University, Taiwan

MLSP-P68.8: Global Context-Aware Multi-Instance Learning for Whole Slide Image Classification
Jiahui Zhang, Yukun Cui, Lancaster University, United Kingdom of Great Britain and Northern Ireland; Zhen Pan, Chengdu Normal University, China; Mei Yang, Southwest Petroleum University, China

MLSP-P68.9: Improving Maximum Margin Backdoor Detection by Class Subspace Decorrelation
Guangmingmei Yang, George Kesidis, David Miller, Pennsylvania State University, United States of America