Over ons

Consortium

Team

AI Vlaanderen

Contact

<h5>Description:</h5>
<p>Repository for reproducing results of our paper &ldquo;Efficient Local Image Descriptors Learned with Autoencoders&rdquo; that is currently under review in IEEE Access. It contains code for training autoencoders and variational autoencoders, performing a hyperparameter sweep over different parameters as described in the paper, and for automatically evaluating the descriptor&rsquo;s performance, both based on the established HPatches benchmark and based on our proposed approximate evaluation method.</p>
<p>&nbsp;</p>

<h5>More Information:</h5>
<ul>
<li><strong>Grand Challenge/Workpackage(s): </strong>GC1 - WP4</li>
<li><strong>Responsible Research Lead:</strong> <a href="mailto:Aleksandra.Pizurica@UGent.be" target="_blank" rel="noopener">Aleksandra Pizurica</a></li>
<li><strong>Authors:</strong> <a href="mailto:nina.zizakic@ugent.be" target="_blank" rel="noopener">Nina Zizakic</a></li>
<li><strong>Programming Language: </strong>Python</li>
<li><a href="https://github.com/nimpy/local-img-descr-ae" target="_blank" rel="noopener">Link to the repository</a></li>
<li><strong>Categories:</strong> Un/Semi-supervised learning, Images</li>
</ul>

<h5>Publications:</h5>
<ul>
<li>N. Zizakic and A. Pizurica, "Efficient Local Image Descriptors Learned with Autoencoders", IEEE Access, 2021, (Submitted)</li>
</ul>

<p>Code for learning local image descriptors with autoencoedrs and variational autoencoders</p>