2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Clicking on the Add button next to a paper title will add that paper to your custom schedule.
Clicking on the Remove button next to a paper will remove that paper from your custom schedule.

SS-EDNN: Special Session: Explainable Deep Neural Networks for Image/Video Processing

Session Type: Poster
Time: Wednesday, September 22, 14:30 - 16:00
Location: Area B
Session Chairs: Arash Mohammadi, Concordia Univ, Yong Man Ro, and Konstantinos Plataniotis, University of Toronto
 
   SS-EDNN.1: X3SEG: MODEL-AGNOSTIC EXPLANATIONS FOR THE SEMANTIC SEGMENTATION OF 3D POINT CLOUDS WITH PROTOTYPES AND CRITICISM
         Nina Felicitas Heide; Fraunhofer IOSB
         Erik Müller; Fraunhofer IOSB
         Janko Petereit; Fraunhofer IOSB
         Michael Heizmann; Karlsruhe Institute of Technology
 
   SS-EDNN.2: EXPLAINING DEEP MODELS THROUGH FORGETTABLE LEARNING DYNAMICS
         Ryan Benkert; Georgia Institute of Technology
         Oluwaseun Joseph Aribido; Georgia Institute of Technology
         Ghassan AlRegib; Georgia Institute of Technology
 
   SS-EDNN.3: EXTRACTING CAUSAL VISUAL FEATURES FOR LIMITED LABEL CLASSIFICATION
         Mohit Prabhushankar; Georgia Institute Of Technology
         Ghassan AlRegib; Georgia Institute Of Technology
 
   SS-EDNN.4: CLASS SPECIFIC INTERPRETABILITY IN CNN USING CAUSAL ANALYSIS
         Ankit Yadu; Samsung Research Institute India, Bangalore
         Suhas P K; Samsung Research Institute India, Bangalore
         Neelam Sinha; International Institute of Information Technology, Bangalore
 
   SS-EDNN.5: UNDERSTANDING AND MANIPULATING NEURAL NET FEATURES USING SPARSE OBLIQUE CLASSIFICATION TREES
         Suryabhan Singh Hada; University of California, Merced
         Miguel Á. Carreira-Perpiñán; University of California, Merced
         Arman Zharmagambetov; University of California, Merced
 
   SS-EDNN.6: SAMPLING THE "INVERSE SET" OF A NEURON
         Suryabhan Singh Hada; University of California, Merced
         Miguel Á. Carreira-Perpiñán; University of California, Merced
 
   SS-EDNN.7: EXPLAINERS IN THE WILD: MAKING SURROGATE EXPLAINERS ROBUST TO DISTORTIONS THROUGH PERCEPTION
         Alexander Hepburn; University of Bristol
         Raul Santos-Rodriguez; University of Bristol