<div dir="ltr"><div dir="ltr"><div class="gmail_default" style="font-size:small"><div class="gmail_default"><div><div><b style="font-size:12.8px;font-family:arial,helvetica,sans-serif">When:</b><span style="font-size:12.8px;font-family:arial,helvetica,sans-serif;font-weight:bold"> Tues</span><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aBn" style="font-size:12.8px;font-family:arial,helvetica,sans-serif;border-bottom:1px dashed rgb(204,204,204)"><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aQJ">day, June 11th at 2<b>:00pm</b></span></span><br></div></div><div style="font-size:12.8px"><b><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aBn" style="border-bottom:1px dashed rgb(204,204,204)"><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aQJ"><font face="arial, helvetica, sans-serif"><br></font></span></span></b></div><div style="font-size:12.8px"><font face="arial, helvetica, sans-serif"><b>Where: </b><span style="font-weight:bold"> </span><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aBn" style="border-bottom:1px dashed rgb(204,204,204)"><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aQJ">TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526</span></span></font></div><div style="font-size:12.8px"><b><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aBn" style="border-bottom:1px dashed rgb(204,204,204)"><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aQJ"><font face="arial, helvetica, sans-serif"><br></font></span></span></b></div><div><font face="arial, helvetica, sans-serif" style="font-size:12.8px"><b>Who: </b></font> <font face="arial, sans-serif"><span style="color:rgb(60,64,67);letter-spacing:0.2px">Mohammadreza Mostajabi</span></font><font face="arial, helvetica, sans-serif" style="font-size:12.8px">, TTIC </font></div><div style="font-size:12.8px"><font face="arial, helvetica, sans-serif"><br></font></div><div style="font-size:12.8px"><font face="arial, helvetica, sans-serif"><br></font></div><div style="font-size:12.8px"><div><b>Title: </b><span style="font-size:small">Learning Rich Representations for Structured Prediction Tasks</span></div><br class="gmail-m_3427093491818984434m_3891286512198594456gmail-Apple-interchange-newline"><div><div><b><font face="arial, helvetica, sans-serif">Abstract: </font></b><span style="font-size:small">We describe an approach to learning rich representations for images, that enable simple and effective predictors in a range of vision tasks involving spatially structured maps. Examples of tasks where one can leverage our approach include semantic segmentation, depth estimation and image colorization. Our key idea is to map small image elements (pixels or superpixels) to feature representations extracted from a sequence of nested regions of increasing extent. These regions are obtained by "zooming out" from the superpixel all the way to scene-level resolution, and hence we call these zoomout features. Applied to semantic segmentation and other structured prediction tasks, our approach exploits statistical structure in the image and in the label space without setting up explicit structured prediction mechanisms, and thus avoids complex and expensive inference. Instead image elements are classified by a feedforward multilayer network with skip-layer connections spanning the zoomout levels.</span></div><br style="font-size:small"><span style="font-size:small">We describe extensive experiments showing the effectiveness of our simple architecture design. When used in conjunction with modern neural architectures such as ResNet, DenseNet and NASNet (to which it is complementary) our approach achieve competitive accuracy on segmentation benchmarks. Finally, we introduce data-driven regularization functions for the supervised training of CNNs. Our innovation takes the form of a regularizer derived by learning an autoencoder over the set of annotations. This approach further complements our zoom-out representation, leveraging an improved representation of label space to inform our extraction of features from images.</span><br class="gmail-m_3427093491818984434m_3891286512198594456gmail-Apple-interchange-newline"><div><br></div></div><br></div><div style="font-size:12.8px"><br></div><span style="font-size:12.8px"><b><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-il"><span class="gmail-il">Thesis</span></span> Advisor: </b> <a href="mailto:greg@ttic.edu" target="_blank">Greg Shakhnarovich</a></span><br clear="all"></div><div class="gmail_default"><br></div><br class="gmail-Apple-interchange-newline"></div><div class="gmail_default" style="font-size:small"><br></div><div class="gmail_default" style="font-size:small"><br></div><div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><font face="arial, helvetica, sans-serif">Mary C. Marre</font><div><font face="arial, helvetica, sans-serif">Administrative Assistant</font></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6"><b>Toyota Technological Institute</b></font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">6045 S. Kenwood Avenue</font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Room 517</font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Chicago, IL 60637</font></i></div><div><i><font face="arial, helvetica, sans-serif">p:(773) 834-1757</font></i></div><div><i><font face="arial, helvetica, sans-serif">f: (773) 357-6970</font></i></div><div><b><i><a href="mailto:mmarre@ttic.edu" target="_blank"><font face="arial, helvetica, sans-serif">mmarre@ttic.edu</font></a></i></b></div></div></div></div></div></div></div></div></div></div></div></div></div></div><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Fri, May 31, 2019 at 11:12 AM Mary Marre <<a href="mailto:mmarre@ttic.edu">mmarre@ttic.edu</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div><div><div><b style="font-size:12.8px;font-family:arial,helvetica,sans-serif">When:</b><span style="font-size:12.8px;font-family:arial,helvetica,sans-serif;font-weight:bold"> Tues</span><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aBn" style="font-size:12.8px;font-family:arial,helvetica,sans-serif;border-bottom:1px dashed rgb(204,204,204)"><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aQJ">day, June 11th at 2<b>:00pm</b></span></span><br></div></div><div style="font-size:12.8px"><b><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aBn" style="border-bottom:1px dashed rgb(204,204,204)"><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aQJ"><font face="arial, helvetica, sans-serif"><br></font></span></span></b></div><div style="font-size:12.8px"><font face="arial, helvetica, sans-serif"><b>Where: </b><span style="font-weight:bold"> </span><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aBn" style="border-bottom:1px dashed rgb(204,204,204)"><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aQJ">TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526</span></span></font></div><div style="font-size:12.8px"><b><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aBn" style="border-bottom:1px dashed rgb(204,204,204)"><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-m_-7788020261563922307gmail-m_-7693139298067466964m_-5276955929831589859gmail-m_-8102197176306466350gmail-m_-7224781006463542997gmail-m_5098382079273635224gmail-aQJ"><font face="arial, helvetica, sans-serif"><br></font></span></span></b></div><div><font face="arial, helvetica, sans-serif" style="font-size:12.8px"><b>Who: </b></font>
<font face="arial, sans-serif"><span style="color:rgb(60,64,67);letter-spacing:0.2px">Mohammadreza Mostajabi</span></font><font face="arial, helvetica, sans-serif" style="font-size:12.8px">, TTIC </font></div><div style="font-size:12.8px"><font face="arial, helvetica, sans-serif"><br></font></div><div style="font-size:12.8px"><font face="arial, helvetica, sans-serif"><br></font></div><div style="font-size:12.8px"><div><b>Title: </b><span style="font-size:small">Learning Rich Representations for Structured Prediction Tasks</span></div><br class="gmail-m_3427093491818984434m_3891286512198594456gmail-Apple-interchange-newline"><div><div><b><font face="arial, helvetica, sans-serif">Abstract: </font></b><span style="font-size:small">We describe an approach to learning rich representations for images, that enable simple and effective predictors in a range of vision tasks involving spatially structured maps. Examples of tasks where one can leverage our approach include semantic segmentation, depth estimation and image colorization. Our key idea is to map small image elements (pixels or superpixels) to feature representations extracted from a sequence of nested regions of increasing extent. These regions are obtained by "zooming out" from the superpixel all the way to scene-level resolution, and hence we call these zoomout features. Applied to semantic segmentation and other structured prediction tasks, our approach exploits statistical structure in the image and in the label space without setting up explicit structured prediction mechanisms, and thus avoids complex and expensive inference. Instead image elements are classified by a feedforward multilayer network with skip-layer connections spanning the zoomout levels.</span></div><br style="font-size:small"><span style="font-size:small">We describe extensive experiments showing the effectiveness of our simple architecture design. When used in conjunction with modern neural architectures such as ResNet, DenseNet and NASNet (to which it is complementary) our approach achieve competitive accuracy on segmentation benchmarks. Finally, we introduce data-driven regularization functions for the supervised training of CNNs. Our innovation takes the form of a regularizer derived by learning an autoencoder over the set of annotations. This approach further complements our zoom-out representation, leveraging an improved representation of label space to inform our extraction of features from images.</span><br class="gmail-m_3427093491818984434m_3891286512198594456gmail-Apple-interchange-newline"><div><br></div></div><br></div><div style="font-size:12.8px"><br></div><span style="font-size:12.8px"><b><span class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail-il">Thesis</span> Advisor: </b> <a href="mailto:greg@ttic.edu" target="_blank">Greg Shakhnarovich</a></span><br clear="all"></div><div><br></div><div><br></div><div><br></div><div><br></div><div><div dir="ltr" class="gmail-m_3427093491818984434m_3891286512198594456m_-4473875513674366096gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><font face="arial, helvetica, sans-serif">Mary C. Marre</font><div><font face="arial, helvetica, sans-serif">Administrative Assistant</font></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6"><b>Toyota Technological Institute</b></font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">6045 S. Kenwood Avenue</font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Room 517</font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Chicago, IL 60637</font></i></div><div><i><font face="arial, helvetica, sans-serif">p:(773) 834-1757</font></i></div><div><i><font face="arial, helvetica, sans-serif">f: (773) 357-6970</font></i></div><div><b><i><a href="mailto:mmarre@ttic.edu" target="_blank"><font face="arial, helvetica, sans-serif">mmarre@ttic.edu</font></a></i></b></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div>
</blockquote></div></div>