<html><body><div style="font-family: garamond,new york,times,serif; font-size: 12pt; color: #000000"><div>Davit Buniatyan will present his general exam on Friday, October 13, 2017 at 4pm in CS 402. </div><div><br data-mce-bogus="1"></div><div>The members of his committee are as follows: Sebastian Seung (adviser), Yoram Singer, and Szymon Rusinkiewicz. Everyone is invited to attend his talk, and those faculty wishing to remain for the oral exam following are welcome to do so. His abstract and reading list follow below.</div><div><br data-mce-bogus="1"></div><div data-marker="__QUOTED_TEXT__">
<div class="">
<div class="">Title: Deep Learning Improves Template Matching by Normalized Cross Correlation</div>
</div>
<div class=""><br class="">
</div>
<div class="">Abstract: Template matching by normalized cross correlation (NCC) is widely used for finding image correspondences. We improve the robustness of this algorithm by preprocessing images with "siamese" convolutional networks trained to maximize the
contrast between NCC values of true and false matches. The improvement is quantified using patches of brain images from serial section electron microscopy. Relative to a parameter-tuned bandpass filter, siamese convolutional networks significantly reduce false
matches. Furthermore, all false matches can be eliminated by removing a tiny fraction of all matches based on NCC values. The improved accuracy of our method could be essential for connectomics, because emerging petascale datasets may require billions of template
matches to assemble 2D images of serial sections into a 3D image stack. Our method is also expected to generalize to many other computer vision applications that use NCC template matching to find image correspondences.</div>
<div class=""><br class="">
</div>
<div class="">
<div style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;" class="" data-mce-style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;">
<b class="">Reading List</b></div>
<ul style="list-style-type: circle;" class="" data-mce-style="list-style-type: circle;">
<li style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;" class="" data-mce-style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;">
Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep Learning, </li><li style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;" class="" data-mce-style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;">
Brian Kulis et al. Metric learning: A survey. Foundations and TrendsR in Machine Learning, 5(4): 287–364, 2013</li><li style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;" class="" data-mce-style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;">
Jane Bromley, James W. Bentz, Léon Bottou, Isabelle Guyon, Yann LeCun, Cliff Moore, Eduard Säckinger, and Roopak Shah. Signature verification using a "siamese" time delay neural network. IJPRAI, 7(4): 669–688, 1993.</li><li style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;" class="" data-mce-style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;">
Sumit Chopra, Raia Hadsell, and Yann LeCun. Learning a similarity metric discriminatively, with application to face verification. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, volume 1, pages 539–546. IEEE,
2005.</li><li style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;" class="" data-mce-style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;">
Han, Xufeng, et al. "Matchnet: Unifying feature and metric learning for patch-based matching."
<i class="">Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition</i>. 2015.</li><li style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;" class="" data-mce-style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;">
Arulkumar Subramaniam, Moitreya Chatterjee, and Anurag Mittal. Deep neural networks with inexact matching for person re-identification. In Advances in Neural Information Processing Systems, pages 2667–2675, 2016.</li><li style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;" class="" data-mce-style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;">
Stephan Saalfeld, Richard Fetter, Albert Cardona, and Pavel Tomancak. Elastic volume reconstruction from series of ultra-thin microscopy sections. Nature methods, 9(7):717–720, 2012.</li><li style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;" class="" data-mce-style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545;">
Jonathan L Long, Ning Zhang, and Trevor Darrell. Do convnets learn correspondence? In Advances in Neural Information Processing Systems, pages 1601–1609, 2014.</li></ul>
<div style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545; min-height: 14px;" class="" data-mce-style="margin: 0px; line-height: normal; font-family: 'Helvetica Neue'; color: #454545; min-height: 14px;">
<br class="">
</div>
</div>
<br></div></div></body></html>