MLSP-15.5
BOUNDARY-AWARE BIAS LOSS FOR TRANSFORMER-BASED AERIAL IMAGE SEGMENTATION MODEL
Yan Zhang, Xue Jiang, Bo Hu, Xinbo Gao, Chongqing University of Posts and Telecommunications, China; Siqi Liu, Peking University, China
Session:
Pattern Recognition and Classification V
Track:
Machine Learning for Signal Processing
Location:
Gather Area G
Presentation Time:
Mon, 9 May, 21:00 - 21:45 China Time (UTC +8)
Mon, 9 May, 13:00 - 13:45 UTC
Mon, 9 May, 13:00 - 13:45 UTC
Session Chair:
Chng Eng Siong, Nanyang Technological University
Session MLSP-15
MLSP-15.1: NEAREST SUBSPACE SEARCH IN THE SIGNED CUMULATIVE DISTRIBUTION TRANSFORM SPACE FOR 1D SIGNAL CLASSIFICATION
Abu Hasnat Mohammad Rubaiyat, Mohammad Shifat-E-Rabbi, Yan Zhuang, Shiying Li, Gustavo Rohde, University of Virginia, United States of America
MLSP-15.2: ENERGY ALIGNMENT FOR BIAS RECTIFICATION IN CLASS INCREMENTAL LEARNING
Bowen Zhao, Xi Xiao, Shutao Xia, Tsinghua University, China; Chen Chen, Qi Ju, Tencent, China
MLSP-15.3: A TWO-STAGE CONTRASTIVE LEARNING FRAMEWORK FOR IMBALANCED AERIAL SCENE RECOGNITION
Lexing Huang, Senlin Cai, Yihong Zhuang, Changxing Jing, Yue Huang, Xiaotong Tu, Xinghao Ding, Xiamen University, China
MLSP-15.4: A Maximal Correlation Approach to Imposing Fairness in Machine Learning
Joshua Lee, Yuheng Bu, Gregory Wornell, MIT, United States of America; Prasanna Sattigeri, Rameswar Panda, Leonid Karlinsky, Rogerio Feris, IBM Research, United States of America
MLSP-15.5: BOUNDARY-AWARE BIAS LOSS FOR TRANSFORMER-BASED AERIAL IMAGE SEGMENTATION MODEL
Yan Zhang, Xue Jiang, Bo Hu, Xinbo Gao, Chongqing University of Posts and Telecommunications, China; Siqi Liu, Peking University, China
MLSP-15.6: INVESTIGATING ROBUSTNESS OF BIOLOGICAL VS. BACKPROP BASED LEARNING
Yanpeng Zhou, Maosen Wang, Ponnuthurai Nagaratnam Suganthan, Nanyang Technological University, Singapore; Manas Gupta, Arulmurugan Ambikapathi, Ramasamy Savitha, A*STAR, Singapore