From Generic to Specific Deep Representations for Visual Recognition
2015 (English)In: Proceedings of CVPR 2015, IEEE conference proceedings, 2015Conference paper (Refereed)
Evidence is mounting that ConvNets are the best representation learning method for recognition. In the common scenario, a ConvNet is trained on a large labeled dataset and the feed-forward units activation, at a certain layer of the network, is used as a generic representation of an input image. Recent studies have shown this form of representation to be astoundingly effective for a wide range of recognition tasks. This paper thoroughly investigates the transferability of such representations w.r.t. several factors. It includes parameters for training the network such as its architecture and parameters of feature extraction. We further show that different visual recognition tasks can be categorically ordered based on their distance from the source task. We then show interesting results indicating a clear correlation between the performance of tasks and their distance from the source task conditioned on proposed factors. Furthermore, by optimizing these factors, we achieve stateof-the-art performances on 16 visual recognition tasks.
Place, publisher, year, edition, pages
IEEE conference proceedings, 2015.
, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, ISSN 2160-7508
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:kth:diva-164527DOI: 10.1109/CVPRW.2015.7301270ISI: 000378887900005ScopusID: 2-s2.0-84951960494ISBN: 978-146736759-2OAI: oai:DiVA.org:kth-164527DiVA: diva2:806070
CVPRW DeepVision Workshop,June 11, 2015, Boston, MA, USA
QC 201505072015-04-172015-04-172016-08-15Bibliographically approved