@mastersthesis {xBosch, title = {Region-oriented Convolutional Networks for Object Retrieval}, year = {2015}, abstract = {

Advisors: Amaia Salvador and\ Xavier Gir{\'o}-i-Nieto\ (UPC)\ 

Study program: Engineering on Audiovisual Systems (4 years) at Escola d{\textquoteright}Enginyeria de Terrassa\ (UPC)

Grade: A (9.6/10)

This thesis is framed in the computer vision field, addressing a challenge related to instance search. Instance search consists in searching for occurrences of a certain visual instance on a large collection of visual content, and generating a ranked list of results sorted according to their relevance to a user query. This thesis builds up on existing work presented at the TRECVID Instance Search Task in 2014, and explores the use of local deep learning features extracted from object proposals. The performance of different deep learning architectures (at both global and local scales) is evaluated, and a thorough comparison of them is performed. Secondly, this thesis presents the guidelines to follow in order to fine-tune a convolutional neural network for tasks such as image classification, object detection and semantic segmentation. It does so with the final purpose of fine tuning SDS, a CNN trained for both object detection and semantic segmentation, with the recently released Microsoft COCO dataset.

Region-oriented Convolutional Networks for Object Retrieval from Xavier Giro
}, author = {Fontdevila-Bosch, Eduard}, editor = {Amaia Salvador and Xavier Gir{\'o}-i-Nieto} }