[visionlist] BMVA Symposium: 2nd Call for Papers "Visual Image Interpretation in Humans and Machines: Machines that see like us?"

[Schofield, Andrew]

BMVA Symposium: Call for Papers "Visual Image Interpretation in Humans and Machines: Machines that see like us?"
One Day BMVA symposium in London, UK on Wednesday 10th April 2019
Chair Andrew Schofield, Aston University

Keynote Speakers
Charles Leek, University of Liverpool, "Deep Neural Networks: The new black box of human vision research?"
Andrew Glennerster, University of Reading, "Policy networks with and without brains"
Tim Kietzmann, MRC Cognition and Brain Science Unit, University of Cambridge,

Submission Deadline 6th February
We encourage submissions from students, academics and practitioners in the area. All those interested in presenting at this meeting are invited to submit an abstract of their talk bmva.weebly.com by 6th February (firm deadline).

Note the temporary website for BMVA technical meetings, www.bmva.weebly.com

Call for Papers
Both the object recognition and game playing performance of deep convolutional neural networks now equals or surpasses that of humans. Deep neural networks share some features in common with the human visual system including multiple layers of processing with the early layers being convolutional in nature. Moreover, techniques such as representational similarity analysis show that appropriately trained neural networks develop representation spaces similar to that of inferior temporal cortex which is known to support object recognition in humans. These results and the superficial similarity in network structure between artificial and biological neural networks lead some to conclude that the former is a good functional model for the latter.

In contrast, others note that deep neural networks are easily fooled by image manipulations that are barely noticeable to humans or by specially constructed image elements that trick artificial networks but are seen but ignored by humans. There are also stark differences between artificial and biological networks with mean features of the latter omitted from artificial systems. There are differences too in the style and rates of learning and generalisation between humans and machines. Such findings suggest that models of human vision should be quite different from deep neural networks.

This one-day meeting will consider the issue in human and machine vision discussing how artificial neural networks might be augmented with more biologically plausible features with the aim of making them more robust, and alternatives to neural network models and how their performance compares to the state of the art and human vision.

Submission Deadline
We encourage submissions from students, academics and practitioners in the area. All those interested in presenting at this meeting are invited to submit an abstract of their talk bmva.weebly.com by 6th February (firm deadline).

Registration:
Register online www.bmva.weebly.com

£16 for BMVA members, £36 for non-members, including lunch