MLSP-7.4
DYNAMICALLY PRUNING SEGFORMER FOR EFFICIENT SEMANTIC SEGMENTATION
Haoli Bai, The Chinese University of Hong Kong, China; Hongda Mao, Dinesh Nair, Amazon.com, United States of America
Session:
Deep Learning for Image and Video Processing I
Track:
Machine Learning for Signal Processing
Location:
Gather Area F
Presentation Time:
Sun, 8 May, 22:00 - 22:45 China Time (UTC +8)
Sun, 8 May, 14:00 - 14:45 UTC
Sun, 8 May, 14:00 - 14:45 UTC
Session Chair:
Kai-Kuang Ma, Nanyang Technological University
Session MLSP-7
MLSP-7.1: TARGETDROP: A TARGETED REGULARIZATION METHOD FOR CONVOLUTIONAL NEURAL NETWORKS
Hui Zhu, Xiaofang Zhao, Institute of Computing Technology, Chinese Academy of Sciences, China
MLSP-7.2: COARSE-TO-FINE UNSUPERVISED CHANGE DETECTION FOR REMOTE SENSING IMAGES VIA OBJECT-BASED MRF AND INCEPTION UNET
Xuan Hou, Haonan Shi, Ying Li, Northwestern Polytechnical University, China; Yunpeng Bai, Aberystwyth University, China
MLSP-7.3: Combating False Sense of Security: Breaking the Defense of Adversarial Training via Non-Gradient Adversarial Attack
Mingyuan Fan, Wenzhong Guo, Ximeng Liu, Fuzhou University, China; Yang Liu, Xidian University, China; Cen Chen, East China Normal University, China; Shengxing Yu, Peking University, China
MLSP-7.4: DYNAMICALLY PRUNING SEGFORMER FOR EFFICIENT SEMANTIC SEGMENTATION
Haoli Bai, The Chinese University of Hong Kong, China; Hongda Mao, Dinesh Nair, Amazon.com, United States of America
MLSP-7.5: Deformable VisTR: Spatio temporal deformable attention for video instance segmentation
Sudhir Yarram, Jialian Wu, Junsong Yuan, University at Buffalo, United States of America; Pan Ji, Yi Xu, OPPO US Research Center, InnoPeak Technology Inc., United States of America
MLSP-7.6: SINGLE IMAGE SUPER-RESOLUTION USING ASYNCHRONOUS MULTI-SCALE NETWORK
Jiahuan Ji, Baojiang Zhong, Soochow University, China; Kai-Kuang Ma, Nanyang Technological University, Singapore