MLSP-5.3
A FREE LUNCH FROM VIT: ADAPTIVE ATTENTION MULTI-SCALE FUSION TRANSFORMER FOR FINE-GRAINED VISUAL RECOGNITION
Yuan Zhang, Jian Cao, Ling Zhang, Xiangcheng Liu, Zhiyi Wang, Feng Ling, Peking University, China; Weiqian Chen, Peking University, Alibaba Group, Inc., China
Session:
Pattern Recognition and Classification II
Track:
Machine Learning for Signal Processing
Location:
Gather Area G
Presentation Time:
Sun, 8 May, 21:00 - 21:45 China Time (UTC +8)
Sun, 8 May, 13:00 - 13:45 UTC
Sun, 8 May, 13:00 - 13:45 UTC
Session Chair:
Zheng-Hua Tan, Aalborg University
Session MLSP-5
MLSP-5.1: LABEL-OCCURRENCE-BALANCED MIXUP FOR LONG-TAILED RECOGNITION
Shaoyu Zhang, Chen Chen, Silong Peng, Institute of Automation, Chinese Academy of Sciences, China; Xiujuan Zhang, Inner Mongolia Key Laboratory of Molecular Biology on Featured Plants, China
MLSP-5.2: TNTC: two-stream network with transformer-based complementarity for gait-based emotion recognition
Chuanfei Hu, Weijie Sheng, Xinde Li, Southeast University, China; Bo Dong, Zhejiang University, China
MLSP-5.3: A FREE LUNCH FROM VIT: ADAPTIVE ATTENTION MULTI-SCALE FUSION TRANSFORMER FOR FINE-GRAINED VISUAL RECOGNITION
Yuan Zhang, Jian Cao, Ling Zhang, Xiangcheng Liu, Zhiyi Wang, Feng Ling, Peking University, China; Weiqian Chen, Peking University, Alibaba Group, Inc., China
MLSP-5.4: Self-supervised Contrastive Learning for Cross-domain Hyperspectral Image Representation
Hyungtae Lee, Heesung Kwon, DEVCOM Army Research Laboratory, United States of America
MLSP-5.5: GOS: A LARGE-SCALE ANNOTATED OUTDOOR SCENE SYNTHETIC DATASET
Mingye Xie, Ting Liu, Yuzhuo Fu, Shanghai Jiao Tong University, China
MLSP-5.6: OUT-OF-DISTRIBUTION AS A TARGET CLASS IN SEMI-SUPERVISED LEARNING
Antoine Tadros, Sébastien Drouyer, Rafael Grompone von Gioi, Ecole Normale Supérieur Paris-Saclay, France