TA1.L3: Applications of Explainable AI
Tue, 29 Oct, 08:30 - 10:00 Gulf Standard Time (UTC +4)
Location: Capital Suite - 15
Session Type: Lecture
Session Chair: Jenni Raitoharju, University of Jyväskylä
Track: Visual Artificial Intelligence
Click the to view the manuscript on IEEE Xplore Open Preview
Tue, 29 Oct, 08:30 - 08:48 Gulf Standard Time (UTC +4)
 

TA1.L3.1: EXPLAINING 3D OBJECT DETECTION THROUGH SHAPLEY VALUE-BASED ATTRIBUTION MAP
Michihiro Kuroki, Toshihiko Yamasaki, The University of Tokyo, Japan
Tue, 29 Oct, 08:48 - 09:06 Gulf Standard Time (UTC +4)
 

TA1.L3.2: FEATURES DISENTANGLEMENT FOR EXPLAINABLE CONVOLUTIONAL NEURAL NETWORKS
Pasquale Coscia, Angelo Genovese, Fabio Scotti, Vincenzo Piuri, Università degli Studi di Milano, Italy
Tue, 29 Oct, 09:06 - 09:24 Gulf Standard Time (UTC +4)
 

TA1.L3.3: EMBEDDING ATTENTION BLOCKS FOR ANSWER GROUNDING
Seyedalireza Khoshsirat, Chandra Kambhamettu, University of Delaware, United States of America
Tue, 29 Oct, 09:24 - 09:42 Gulf Standard Time (UTC +4)
 

TA1.L3.4: ENHANCED PROTOTYPICAL PART NETWORK (EPPNET) FOR EXPLAINABLE IMAGE CLASSIFICATION VIA PROTOTYPES
Bhushan Atote, Student, United Kingdom of Great Britain and Northern Ireland; Victor Sanchez, Professor, United Kingdom of Great Britain and Northern Ireland
Tue, 29 Oct, 09:42 - 10:00 Gulf Standard Time (UTC +4)
 

TA1.L3.5: INTERACTIVE TEACHING FOR FINE-GRANULAR FEW-SHOT OBJECT RECOGNITION USING VISION TRANSFORMERS
Philip Keller, FZI Research Center for Information Technology, Germany; Daniel Jost, Karlsruhe Institute of Technology, Germany; Arne Roennau, Rüdiger Dillmann, FZI Research Center for Information Technology, Germany