Technical Program

Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICIP 2019 Open Preview.

WP.L7: Special Session - Explainable Machine Learning for Image Processing

Session Type: Lecture
Time: Wednesday, September 25, 14:10 - 15:58
Location: Room 201DE (2F)
Session Chairs: Konstantinos Plataniotis, University of Toronto and Arash Mohammadi, Concordia University
 
 WP.L7.1: ENSEMBLES OF FEEDFORWARD-DESIGNED CONVOLUTIONAL NEURAL NETWORKS
         Yueru Chen; University of Southern California
         Yijing Yang; University of Southern California
         Wei Wang; University of Southern California
         C.-C. Jay Kuo; University of Southern California
 
 WP.L7.2: IMPROVING ROBUSTNESS TO ADVERSARIAL EXAMPLES BY ENCOURAGING DISCRIMINATIVE FEATURES
         Chirag Agarwal; University of Illinois at Chicago
         Anh Nguyen; Auburn University
         Dan Schonfeld; University of Illinois at Chicago
 
 WP.L7.3: TOWARDS EXPLAINABLE FACE AGING WITH GENERATIVE ADVERSARIAL NETWORKS
         Angelo Genovese; Università degli Studi di Milano
         Vincenzo Piuri; Università degli Studi di Milano
         Fabio Scotti; Università degli Studi di Milano
 
 WP.L7.4: WHEN CAUSAL INTERVENTION MEETS ADVERSARIAL EXAMPLES AND IMAGE MASKING FOR DEEP NEURAL NETWORKS
         Chao-Han Huck Yang; Georgia Institute of Technology
         Yi-Chieh Liu; Georgia Institute of Technology
         Pin-Yu Chen; IBM Research
         Xiaoli Ma; Georgia Institute of Technology
         Yi-Chang James Tsai; Georgia Institute of Technology
 
 WP.L7.5: CAPSULE NETWORKS' INTERPRETABILITY FOR BRAIN TUMOR CLASSIFICATION VIA RADIOMICS ANALYSES
         Parnian Afshar; Concordia University
         Konstantinos N. Plataniotis; University of Toronto
         Arash Mohammadi; Concordia University
 
 WP.L7.6: PROBENET: PROBING DEEP NETWORKS
         Jae-Hyeok Lee; Korea Advanced Institute of Science and Technology (KAIST)
         Seong Tae Kim; Korea Advanced Institute of Science and Technology (KAIST)
         Yong Man Ro; Korea Advanced Institute of Science and Technology (KAIST)