A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit <a rel="external noopener" href="http://www.ee.cuhk.edu.hk:80/~xgwang/papers/wangOWLcvpr16.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)</a>
Due to the limited amount of training samples, finetuning pre-trained deep models online is prone to overfitting. In this paper, we propose a sequential training method for convolutional neural networks (CNNs) to effectively transfer pre-trained deep features for online applications. We regard a CNN as an ensemble with each channel of the output feature map as an individual base learner. Each base learner is trained using different loss criterions to reduce correlation and avoid over-training.<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2016.153">doi:10.1109/cvpr.2016.153</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/WangOWL16.html">dblp:conf/cvpr/WangOWL16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/c7rbqdxnvfdhdc7g4zxx2zviou">fatcat:c7rbqdxnvfdhdc7g4zxx2zviou</a> </span>
more »... o achieve the best ensemble online, all the base learners are sequentially sampled into the ensemble via important sampling. To further improve the robustness of each base learner, we propose to train the convolutional layers with random binary masks, which serves as a regularization to enforce each base learner to focus on different input features. The proposed online training method is applied to visual tracking problem by transferring deep features trained on massive annotated visual data and is shown to significantly improve tracking performance. Extensive experiments are conducted on two challenging benchmark data set and demonstrate that our tracking algorithm can outperform state-of-the-art methods with a considerable margin.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160909083844/http://www.ee.cuhk.edu.hk:80/~xgwang/papers/wangOWLcvpr16.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3a/c6/3ac65f7f0413fd4d5f7ec0a61c9b1c1fed61bb82.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2016.153"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>