MP2.L6.4
VITO: VISION TRANSFORMER OPTIMIZATION VIA KNOWLEDGE DISTILLATION ON DECODERS
Giovanni Bellitto, Renato Sortino, Paolo Spadaro, Simone Palazzo, Federica Proietto Salanitri, University of Catania, Italy; Giuseppe Fiameni, NVIDIA, Italy; Efstratios Gavves, University of Amsterdam, Netherlands; Concetto Spampinato, University of Catania, Italy
Session:
MP2.L6: Training and Supervision Strategies for Image & Video Data - II Lecture
Track:
Visual Artificial Intelligence
Location:
Lecture Room 6
Presentation Time:
Mon, 28 Oct, 17:24 - 17:42 Gulf Standard Time (UTC +4)
Session Chair:
Simone Palazzo, University of Catania
Session MP2.L6
MP2.L6.1: Learning Orthonormal Features in Self-Supervised Learning using Functional Maximal Correlation
Bo Hu, Yuheng Bu, José C. Príncipe, University of Florida, United States of America
MP2.L6.2: ADAPTIVE ADVERSARIAL CROSS-ENTROPY LOSS FOR SHARPNESS-AWARE MINIMIZATION
Tanapat Ratchatorn, Masayuki Tanaka, Institute of Science Tokyo, Japan
MP2.L6.3: REINFORCING PRE-TRAINED MODELS USING COUNTERFACTUAL IMAGES
Xiang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, Hokkaido University, Japan
MP2.L6.4: VITO: VISION TRANSFORMER OPTIMIZATION VIA KNOWLEDGE DISTILLATION ON DECODERS
Giovanni Bellitto, Renato Sortino, Paolo Spadaro, Simone Palazzo, Federica Proietto Salanitri, University of Catania, Italy; Giuseppe Fiameni, NVIDIA, Italy; Efstratios Gavves, University of Amsterdam, Netherlands; Concetto Spampinato, University of Catania, Italy
MP2.L6.5: Video Class-Incremental Learning with CLIP based Transformer
Shuyun Lu, Jian Jiao, Lanxiao Wang, Heqian Qiu, Xingtao Lin, Hefei Mei, Hongliang Li, University of Electronic Science and Technology of China, China
Contacts