MA1.L3: Explainable AI Methods
Mon, 28 Oct, 08:30 - 10:00 Gulf Standard Time (UTC +4)
Location: Capital Suite - 16
Session Type: Lecture
Session Chair: Akka Zemmari, LaBRI, University of Bordeaux
Track: Visual Artificial Intelligence
Click the to view the manuscript on IEEE Xplore Open Preview
Mon, 28 Oct, 08:30 - 08:48 Gulf Standard Time (UTC +4)
 

MA1.L3.1: EXPLAINING REPRESENTATION LEARNING WITH PERCEPTUAL COMPONENTS
Yavuz Yarici, Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib, Georgia Institute of Technology, United States of America
Mon, 28 Oct, 08:48 - 09:06 Gulf Standard Time (UTC +4)
 

MA1.L3.2: ET: EXPLAIN TO TRAIN: LEVERAGING EXPLANATIONS TO ENHANCE THE TRAINING OF A MULTIMODAL TRANSFORMER
Meghna P Ayyar, Jenny Benois-Pineau, Akka Zemmari, LaBRI, University of Bordeaux, France
Mon, 28 Oct, 09:06 - 09:24 Gulf Standard Time (UTC +4)
 

MA1.L3.3: Saliency as a Schedule: Intuitive Image Attribution
Aniket Singh, Anoop Namboodiri, International Institute of Information Technology, Hyderabad, India
Mon, 28 Oct, 09:24 - 09:42 Gulf Standard Time (UTC +4)
 Top 5%

MA1.L3.4: ATAC-NET: ZOOMED VIEW WORKS BETTER FOR ANOMALY DETECTION
Shaurya Gupta, Neil Gautam, Anurag Malyala, HyperVerge AI, India
Mon, 28 Oct, 09:42 - 10:00 Gulf Standard Time (UTC +4)
 

MA1.L3.5: ROTATED R-CNN: A TWO-STAGE OBJECT DETECTION METHOD ADAPTED TO ORIENTED BOUNDING BOXES
Chengdao Pu, Jun Yu, University of Science and Technology of China, China; Wen Su, Zhejiang Sci-Tech University, China; Tianyu Liu, Jianghuai Advance Technology Center, China; ,