Please use this identifier to cite or link to this item: http://repositorio.inesctec.pt/handle/123456789/6017
Title: Pre-trained convolutional networks and generative statistical models: A comparative study in large datasets
Authors: Michael,J
Luís Filipe Teixeira
Issue Date: 2017
Abstract: This study explored the viability of out-the-box, pre-trained ConvNet models as a tool to generate features for large-scale classification tasks. A juxtaposition with generative methods for vocabulary generation was drawn. Both methods were chosen in an attempt to integrate other datasets (transfer learning) and unlabelled data, respectively. Both methods were used together, studying the viability of a ConvNet model to estimate category labels of unlabelled images. All experiments pertaining to this study were carried out over a two-class set, later expanded into a 5-category dataset. The pre-trained models used were obtained from the Caffe Model Zoo. The study showed that the pre-trained model achieved best results for the binary dataset, with an accuracy of 0.945. However, for the 5-class dataset, generative vocabularies outperformed the ConvNet (0.91 vs. 0.861). Furthermore, when replacing labelled images with unlabelled ones during training, acceptable accuracy scores were obtained (as high as 0.903). Additionally, it was observed that linear kernels perform particularly well when utilized with generative models. This was especially relevant when compared to ConvNets, which require days of training even when utilizing multiple GPUs for computations. © Springer International Publishing AG 2017.
URI: http://repositorio.inesctec.pt/handle/123456789/6017
http://dx.doi.org/10.1007/978-3-319-58838-4_8
metadata.dc.type: conferenceObject
Publication
Appears in Collections:CTM - Articles in International Conferences

Files in This Item:
File Description SizeFormat 
P-00N-DF4.pdf215.21 kBAdobe PDFThumbnail
View/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.