This thesis is framed in the computer vision eld, 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 di erent 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 ne-tune a convolutional neural network for tasks such as image classi cation, object detection and semantic segmentation. It does so with the nal purpose of ne tuning SDS, a CNN trained for both object detection and semantic segmentation, with the recently released Microsoft COCO dataset.