<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"><head><META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=us-ascii"><meta name=Generator content="Microsoft Word 15 (filtered medium)"><style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
h5
{mso-style-priority:9;
mso-style-link:"\0395\03C0\03B9\03BA\03B5\03C6\03B1\03BB\03AF\03B4\03B1 5 Char";
mso-margin-top-alt:auto;
margin-right:0in;
mso-margin-bottom-alt:auto;
margin-left:0in;
font-size:10.0pt;
font-family:"Calibri",sans-serif;
font-weight:bold;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#0563C1;
text-decoration:underline;}
span.5Char
{mso-style-name:"\0395\03C0\03B9\03BA\03B5\03C6\03B1\03BB\03AF\03B4\03B1 5 Char";
mso-style-priority:9;
mso-style-link:"\0395\03C0\03B9\03BA\03B5\03C6\03B1\03BB\03AF\03B4\03B1 5";
font-family:"Calibri",sans-serif;
mso-fareast-language:EL;
font-weight:bold;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.25in 1.0in 1.25in;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]--></head><body lang=EL link="#0563C1" vlink="#954F72" style='word-wrap:break-word'><div class=WordSection1><h5 style='margin:0in'><span lang=EN-US style='font-size:11.0pt'>COURSE TITLE: </span><span lang=EN-US style='font-size:11.0pt;font-weight:normal'>Domain Adaptation & Generalization</span><span lang=EN-US style='font-weight:normal'><o:p></o:p></span></h5><h5 style='margin:0in'><span lang=EN-US style='font-size:11.0pt'>LECTURER: </span><span lang=EN-US style='font-size:11.0pt;font-weight:normal'>Vittorio Murino, </span><span style='font-size:11.0pt;color:#1155CC;font-weight:normal'><a href="mailto:vittorio.murino@univr.it" target="_blank"><span lang=EN-US style='font-size:10.0pt'>vittorio.murino@univr.it</span></a></span><span lang=EN-US style='font-size:11.0pt;color:black;font-weight:normal'>; Pietro Morerio</span><span lang=EN-US style='font-size:11.0pt;color:#1155CC;font-weight:normal'>, </span><span style='font-size:11.0pt;color:#1155CC;font-weight:normal'><a href="mailto:pietro.morerio@iit.it" target="_blank"><span lang=EN-US style='font-size:10.0pt'>pietro.morerio@iit.it</span></a></span><span lang=EN-US style='font-weight:normal'><o:p></o:p></span></h5><h5 style='margin:0in'><span lang=EN-US style='font-size:11.0pt'>ORGANIZER: </span><span lang=EN-US style='font-size:11.0pt;font-weight:normal'>University of Verona and Istituto Italiano di Tecnologia</span><span lang=EN-US><o:p></o:p></span></h5><h5 style='margin:0in'><span lang=EN-US style='font-size:11.0pt'>CONTENT AND ORGANIZATION: </span><span lang=EN-US style='font-size:11.0pt;font-weight:normal'>A standard assumption of learning based models is that training and test data share the same input distribution. However, models trained on given datasets perform poorly when tested on data acquired in different settings. This problem is known as domain shift and is particularly relevant, e.g., for visual models of agents acting in the real world or when we have no labeled data available for our target scenario. In the latter case, for instance, we could use synthetically generated data to obtain data for our target task, but this would create a mismatch between training (synthetic) and test (real) images. Filling the gap between these two different input distributions is the goal of domain adaptation (DA) algorithms. In particular, the goal of DA is to produce a model for a target domain (for which we have few or no labeled data) by exploiting labeled data available in a different, source, domain. Various DA techniques have been developed to address the domain shift problem. In this short course, we will provide an introduction to these algorithms and to domain adaptation and generalization. In particular, we will first introduce the domain shift problem, showing application scenarios where it is strongly present. Second, we will provide an overview of the algorithms that have been developed to tackle this issue. In particular, we will focus on the last research trends addressing the DA problem within deep neural networks. Lastly, we will address the domain generalization problem, which is a more challenging task because it assumes that target data is also not available, implying that the training algorithm should be devised to generalize as much as possible without any adaptation to the target in order to properly classify never observed, out-of-distribution samples.</span><span lang=EN-US style='font-weight:normal'><o:p></o:p></span></h5><p class=MsoNormal><span lang=EN-US><o:p> </o:p></span></p><p style='margin:0in'><b><span lang=EN-US>REGISTRATION</span></b><span lang=EN-US>: Free of charge<o:p></o:p></span></p><p style='margin:0in'><span lang=EN-US> <o:p></o:p></span></p><p style='margin:0in'><b><span lang=EN-US>WHEN</span></b><span lang=EN-US>: April 6, 2022 - 14.00-18.00 CET<o:p></o:p></span></p><p style='margin:0in'><span lang=EN-US> <o:p></o:p></span></p><p style='margin:0in'><b><span lang=EN-US>WHERE</span></b><span lang=EN-US>: Online (link to be provided by the Lecturer after registration/enrollment)<o:p></o:p></span></p><p style='margin:0in'><span lang=EN-US style='color:#500050'> <o:p></o:p></span></p><p style='margin:0in'><b><span lang=EN-US>HOW TO REGISTER and ENROLL: <o:p></o:p></span></b></p><p style='margin:0in'><span lang=EN-US>Both AIDA and non-AIDA students are encouraged to participate in this short course. <o:p></o:p></span></p><p style='margin:0in'><span lang=EN-US><o:p> </o:p></span></p><p style='margin:0in'><span lang=EN-US>If you are an AIDA Student* already, please: <o:p></o:p></span></p><p style='margin:0in'><span lang=EN-US>Step (a): Register in the course by sending an email to pietro.morerio[at]</span><a href="http://iit.it/" target="_blank"><span lang=EN-US>iit.it</span></a><span lang=EN-US> for your registration. <o:p></o:p></span></p><p style='margin:0in'><span lang=EN-US>AND <o:p></o:p></span></p><p style='margin:0in'><span lang=EN-US>Step (b): Enroll in the same course in the AIDA system using the button below, so that this course enters your AIDA Certificate of Course Attendance. <o:p></o:p></span></p><p style='margin:0in'><span lang=EN-US><o:p> </o:p></span></p><p style='margin:0in'><span lang=EN-US>If you are not an AIDA Student do only step (a). <o:p></o:p></span></p><p style='margin:0in'><span lang=EN-US><o:p> </o:p></span></p><p style='margin:0in'><span lang=EN-US>*The International AI Doctoral Academy (AIDA) has 73 members, which are top AI Universities, Research centers and Industries: </span><span style='color:#500050'><a href="https://es.sonicurlprotection-fra.com/click?PV=2&MSGID=202202271559430166979&URLID=3&ESV=10.0.15.7233&IV=BB037ED3B12F2777180E2FE00438846D&TT=1645977584923&ESN=%2FwqscGludfJ5ZK96xMM5VPA%2FydclXWMakKctvxs0k%2FE%3D&KV=1536961729280&B64_ENCODED_URL=aHR0cHM6Ly93d3cuaS1haWRhLm9yZy8&HK=26993ACB83D95EAF8317C1C7BF9186A3E3AA1B22217DD0908BCE3AA33B4A2627" target="_blank"><span lang=EN-US>https://www.i-aida.org/</span></a></span><span lang=EN-US style='color:#500050'><o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>AIDA Students should have been registered in the AIDA system already (they are PhD students or PostDocs that belong only to the AIDA Members listed in this page:<span style='color:#500050'> </span></span><span style='color:#500050'><a href="https://es.sonicurlprotection-fra.com/click?PV=2&MSGID=202202271559430166979&URLID=1&ESV=10.0.15.7233&IV=B2A1D7FA8A1918941E8C560177C33C06&TT=1645977584923&ESN=i%2B%2BnSdQCGpTb9fthJLBydzqhw49U25GdbhRwiH%2Fbj%2B0%3D&KV=1536961729280&B64_ENCODED_URL=aHR0cHM6Ly93d3cuaS1haWRhLm9yZy9hYm91dC9tZW1iZXJzLw&HK=96B88288F267D1C8CD7204AD7A248EF36C1112EDC1123E6DC0BCD76D646BE1AA" target="_blank"><span lang=EN-US>Members</span></a></span><span lang=EN-US style='color:#500050'>)<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US><o:p> </o:p></span></p><p class=MsoNormal><span lang=EN-US><o:p> </o:p></span></p><p class=MsoNormal><span lang=EN-US>See more: <a href="https://bit.ly/3wfVTXj" target="_blank">https://bit.ly/3wfVTXj</a><o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US><o:p> </o:p></span></p><p class=MsoNormal><span lang=EN-US><o:p> </o:p></span></p></div><div id="DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2"><br />
<table style="border-top: 1px solid #D3D4DE;">
<tr>
<td style="width: 55px; padding-top: 13px;"><a href="https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=emailclient" target="_blank"><img src="https://ipmcdn.avast.com/images/icons/icon-envelope-tick-round-orange-animated-no-repeat-v1.gif" alt="" width="46" height="29" style="width: 46px; height: 29px;" /></a></td>
<td style="width: 470px; padding-top: 12px; color: #41424e; font-size: 13px; font-family: Arial, Helvetica, sans-serif; line-height: 18px;">Virus-free. <a href="https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=emailclient" target="_blank" style="color: #4453ea;">www.avast.com</a>
</td>
</tr>
</table><a href="#DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2" width="1" height="1"> </a></div></body></html>