publication . Part of book or chapter of book . Conference object . 2016

Comparison of Fine-Tuning and Extension Strategies for Deep Convolutional Neural Networks

Nikiforos Pittaras; Foteini Markatopoulou; Vasileios Mezaris; Ioannis Patras;
Open Access English
  • Published: 31 Dec 2016
  • Publisher: Springer International Publishing
In this study we compare three different fine-tuning strategies in order to investigate the best way to transfer the parameters of popular deep convolutional neural networks that were trained for a visual annotation task on one dataset, to a new, considerably different dataset. We focus on the concept-based image/video annotation problem and use ImageNet as the source dataset, while the TRECVID SIN 2013 and PASCAL VOC-2012 classification datasets are used as the target datasets. A large set of experiments examines the effectiveness of three fine-tuning strategies on each of three different pre-trained DCNNs and each target dataset. The reported results give rise...
Persistent Identifiers
free text keywords: Fine-tuning, TRECVID, Convolutional neural network, Machine learning, computer.software_genre, computer, Computer science, Annotation, Deep learning, Artificial intelligence, business.industry, business, Video annotation
Funded by
In Video Veritas – Verification of Social Media Video Content for the News Industry
  • Funder: European Commission (EC)
  • Project Code: 687786
  • Funding stream: H2020 | IA
Validated by funder
Download fromView all 3 versions
Open Access
Part of book or chapter of book
Provider: UnpayWall
Open Access
Conference object . 2016
Provider: ZENODO
Lecture Notes in Computer Science
Part of book or chapter of book
Provider: Sygma
Part of book or chapter of book . 2016
Provider: Crossref
Any information missing or wrong?Report an Issue