Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/428399
Title: | Multisource Subnetwork Level Transfer in Deep CNNs Using Bank of Weight Filters |
Researcher: | Kirthi, Suresh K |
Guide(s): | Ramakrishnan, K R and Sastry, P S |
Keywords: | Engineering Engineering and Technology Engineering Electrical and Electronic |
University: | Indian Institute of Science Bangalore |
Completed Date: | 2019 |
Abstract: | The convolutional neural networks (CNNs) have become the most successful models for many pattern recognition problems in the areas of computer vision, speech, text and others. One concern about CNNs has always been their need for large amount of training data, large computational re- sources and long training time. In this regard the transfer learning is a technique that can address this concern of inefficient CNN training through reuse of pretrained networks (CNNs). In this thesis we discuss transfer learning in CNNs where the transfer is from multiple source CNNs and done at subnetwork levels. The subnetwork multisource transfer is attempted for the fi rst time and hence we begin by showing the effectiveness of such a transfer. We consider subnetworks at various granularities for the transfer. These granularities begin at a whole network-level then pro-ceed to layer-level and further fi lter-level. In order to realize this kind of transfer we create a set called bank of weight fi lters (BWF) which is a repository of the pretrained subnetworks that are used as candidates for transfer. Through extensive simulations we show that subnetwork level transfer, implemented through random selection from a BWF, is elective and is also efficient in terms of training time. We also present experimental results to show that subnetwork level transfer learning is efficient in terms of the amount of training data needed. It is seen that fi lter-level transfer learning is as effective as the whole-network-level transfer which is the conventional transfer learning used with CNNs. We then show the usefulness of the fi lter-level multisource transfer for the cases of transfer from natural to non-natural (hand drawn sketches) image datasets and transfer across different CNN architectures (having different number of layers, fi lter dimensions etc.). We also discuss transfer from CNNs trained on high-resolution images to the CNNs needed for the low-resolution im- ages and vice-versa. In the multisource transfer of prelearnt weights ... |
Pagination: | xvii , 108 |
URI: | http://hdl.handle.net/10603/428399 |
Appears in Departments: | Electrical Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 71.77 kB | Adobe PDF | View/Open |
02_prelim pages.pdf | 274.5 kB | Adobe PDF | View/Open | |
03_table of contents.pdf | 51.71 kB | Adobe PDF | View/Open | |
04_abstract.pdf | 46.82 kB | Adobe PDF | View/Open | |
05_chapter 1.pdf | 936.21 kB | Adobe PDF | View/Open | |
06_chapter 2.pdf | 837.64 kB | Adobe PDF | View/Open | |
07_chapter 3.pdf | 2.03 MB | Adobe PDF | View/Open | |
08_chapter 4.pdf | 732.05 kB | Adobe PDF | View/Open | |
09_chapter 5.pdf | 6.67 MB | Adobe PDF | View/Open | |
10_chapter 6.pdf | 7.33 MB | Adobe PDF | View/Open | |
11_annexure.pdf | 309.41 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 159.22 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: