Open AccessAn Improved Deep Neural Network Model Based on Searching Space Limitation for Object Localization
Author(s) -
Renchao Wu
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/790/1/012146
Subject(s) - benchmark (surveying) , computer science , artificial intelligence , object (grammar) , space (punctuation) , pattern recognition (psychology) , artificial neural network , image (mathematics) , computer vision , data mining , operating system , geodesy , geography
Image object localization is the primary research direction in computer vision. A lots of algorithms had been proposed based on the ResNet structure and good results have been obtained on mainstream datasets. However, these methods still have the problem of too large ROI search space on weakly supervised data. This paper proposes a method that further limits the search space by directly extracting the high-level parameters of ResNet. The better search results and search efficiency are achieved and the candidate ROI search space is better reduced. The space information of the original images can be retained and training/testing time can be saved. The experimental results on the benchmark datasets show that this network structure has good object localization accuracy under weakly supervised data and the search efficiency is improved compared to other methods.