Please use this identifier to cite or link to this item:
Title: Unsupervised segmentation using CNNs applied to food analysis
Author: Brufau Vidal, Montserrat
Ferrer Campo, Àlex
Gavalas, Markos
Director/Tutor: Radeva, Petia
Keywords: Algorismes computacionals
Visió per ordinador
Tesis de màster
Xarxes neuronals (Informàtica)
Aprenentatge automàtic
Computer algorithms
Computer vision
Masters theses
Neural networks (Computer science)
Machine learning
Issue Date: 3-Jul-2018
Abstract: [en] In the recent times, there have been numerous papers on deep segmentation algorithms for vision tasks. The main challenge of these tasks is to obtain sufficient supervised pixel-level labels for the ground truth. The main goal of this project is to explore if Convolutional Neural Networks can be used for unsupervised segmentation. We follow a novel unsupervised deep architecture, capable of facing this challenge, called the W-net and we test it on food images. The main idea of this model is to concatenate two fully convolutional networks together into an autoencoder. The encoding layer produces a k-way pixelwise prediction, and both the reconstruction error of the autoencoder as well as the error from the decoder are jointly minimized during training. We search for the best architecture for this network and we compare the results for this unsupervised network with supervised results from a well-known network.
Note: Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona, Any: 2018, Tutor: Petia Radeva
Appears in Collections:Programari - Treballs de l'alumnat
Màster Oficial - Fonaments de la Ciència de Dades

Files in This Item:
File Description SizeFormat 
Brufau_Ferrer_Gavalas_TFM.pdfMemòria13.69 MBAdobe PDFView/Open
DATA-SCIENCE-BOWL-2018-master.zipCodi font82.29 MBzipView/Open

This item is licensed under a Creative Commons License Creative Commons