Conference paper Open Access

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

Pittaras, Nikiforos; Markatopoulou, Foteini; Mezaris, Vasileios; Patras, Ioannis

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 to guidelines for effectively fine-tuning a DCNN for concept-based visual annotation.

Files (255.0 kB)
Name Size
mmm17_1_preprint.pdf
md5:a0fcfbb9f6eec5eb87e83b1dde238408
255.0 kB Download
31
34
views
downloads
Views 31
Downloads 34
Data volume 8.7 MB
Unique views 31
Unique downloads 32

Share

Cite as