WP1.L305.2
ADA-VIT: ATTENTION-GUIDED DATA AUGMENTATION FOR VISION TRANSFORMERS
Nada Baili, Hichem Frigui, University of Louisville, United States of America
Session:
WP1.L305: Computational Imaging Learning-Based Models Lecture
Track:
Applications of Machine Learning
Location:
Room 305
Presentation Time:
Wed, 11 Oct, 14:48 - 15:06 Malaysia Time (UTC +8)
Session Chair:
Alessandro Artusi, CYENS CoE
Session WP1.L305
WP1.L305.1: FUZZY-CONDITIONED DIFFUSION AND DIFFUSION PROJECTION ATTENTION APPLIED TO FACIAL IMAGE CORRECTION
Majed El Helou, ETH Zurich, Switzerland
WP1.L305.2: ADA-VIT: ATTENTION-GUIDED DATA AUGMENTATION FOR VISION TRANSFORMERS
Nada Baili, Hichem Frigui, University of Louisville, United States of America
WP1.L305.3: Combining Self-Supervised and Supervised Learning with Noisy Labels
Yongqi Zhang, Hui Zhang, 4Paradigm Inc., China; Quanming Yao, Tsinghua University, China; Jun Wan, Institute of Automation, Chinese Academy of Sciences, China
WP1.L305.4: Parallel Gradient Blend for Class Incremental Learning
Yunlong Zhao, XiaoHeng Deng, Xinjun Pei, Xuechen Chen, Deng Li, Central South University, China
WP1.L305.5: DP-NET: LEARNING DISCRIMINATIVE PARTS FOR IMAGE RECOGNITION
Ronan Sicre, Hanwei Zhang, Julien Dejasmin, LIS, France; Chiheb Daaloul, Ecole Centrale Marseille, France; Stephane Ayache, Thierry Artieres, LIS, France
Contacts