MBCC 2017 - International Workshop on Mutual Benefits of Cognitive and Computer Vision (MBCC)

As researchers working at the intersection of biological and machine vision, we have noticed an increasing interest in both communities to understand and improve on each other’s insights. Recent advances in machine learning (especially deep learning) have led to unprecedented improvements in computer vision. These deep learning algorithms have revolutionized computer vision, and now rival humans at some narrowly defined tasks such as object recognition (e.g., the ImageNet Large Scale Visual Recognition Challenge). In spite of these advances, the existence of adversarial images (some of which have perturbations imperceptible to humans) and rather poor generalizability across datasets point out the flaws present in these networks. On the other hand, the human visual system remains highly efficient at solving real-world tasks and capable of solving many visual tasks. We believe that the time is ripe to have extended discussions and interactions between researchers from both fields in order to steer future research in more fruitful directions. This workshop will compare human vision to state-of-the-art machine perception methods, with specific emphasis on deep learning models and architectures.
Our workshop will address many important questions. They include: 1) What are the representational differences between human and machine perception? 2) What makes human vision so effective? and 3) What can we learn from human vision research? Addressing these questions is not as difficult as previously thought due to technological advancements in both computational science and neuroscience. We can now measure human behavior precisely and collect huge amounts of neurophysiological data using EEG and fMRI. This places us in a unique position to compare state-of-the-art computer vision models and human behavioral/neural data, which was impossible to do a few years ago. However, this advantage also comes with its own set of problems: Which task/metric to use for comparison? What are the representational similarities? How different are the computations in a biological visual system when compared to an artificial vision system? How does human vision achieve invariance?
This workshop is a great opportunity for researchers working on human and/or machine perception to come together and discuss plausible solutions to some of the aforementioned problems.
---
Topics for submission include but are not limited to:
architectures for processing visual information in the human brain and computer vision (e.g. feedforward vs feedback, shallow vs deep networks, residual, recurrent, etc)
limitations of existing computer vision/deep learning systems compared to human vision
learning rules employed in computer vision and by the brain (e.g. unsupervised/semi-supervised learning, Hebb rule, Spike timing dependent plasticity)
representations/features in humans and computer vision
tasks/metrics to compare human and computer vision (e.g. eye fixation, reaction time, rapid categorization, visual search)
new benchmarks (e.g. datasets)
generalizability of machine representation to other tasks
new techniques to measure and analyze human psychophysics and neural signals
the problem on invariant learning
conducting large-scale behavioral and physiological experiments (e.g., fMRI, cell recording)
---
Invited Speakers
We have invited leading researchers from both Cognitive Science and Computer Vision to inspire discussions and collaborations.
Michael Tarr, Carnegie Mellon University
Davide Zoccolan, International School for Advanced Studies (SISSA), Trieste, Italy
---
Submission Guidelines
We are inviting both full paper (5-8 pages) and extended abstract (2-4 pages) submissions to the workshop. Submitted papers must follow the ICCV paper format and guidelines (available on the ICCV 2017 webpage). All submissions will be handled via the CMT website: https://cmt3.research.microsoft.com/MBCC2017/
Full papers: The submitted papers should have a maximum length of 8 pages, including figures and tables; additional pages must contain only cited references. The review will be double-blind. Please make sure all authors or references to authors are anonymized. Full paper submissions must not have been published before.
Extended abstracts: We invite submissions of extended abstracts of ongoing or already published work as well as demos or prototype systems (ICCV format). Authors are given the opportunity to present their work to the right audience. The review will be single-blind.
---
Important Dates
Full Paper submission: August 1st, 2017
Extended Abstract submission: August 5th, 2017
Notification of acceptance: August 15th, 2017
Camera-ready paper due: September 30th, 2017
Workshop: October 29th, 2017 (Morning Session)
---
Workshop Organizing Committee
Ali Borji, University of Central Florida
Pramod RT, Indian Institute of Science
Elissa Aminoff, Fordham University
Christopher Kanan, Rochester Institute of Technology
---
Contact
mbccw.iccv2017-AT-gmail.com