An Iterative Transfer Learning based Classification framework

Yang, Jihai; Li, Shijun; Xu, Wenning

doi:10.1109/ijcnn.2018.8489471

Cited by 1 publication

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since setting hyperparameters of CNNs and parameters of their training has many close-to's, the method of the TLCNN size reduction is not the only feasible [24], [25]. It is plausible that changing some training parameters may allow decreasing numbers of filters further.…”

Section: Discussionmentioning

confidence: 99%

An Efficient Technique for Size Reduction of Convolutional Neural Networks after Transfer Learning for Scene Recognition Tasks

Romanuke

2018

Applied Computer Systems

View full text Add to dashboard Cite

A complex classification task as scene recognition is considered in the present research. Scene recognition tasks are successfully solved by the paradigm of transfer learning from pretrained convolutional neural networks, but a problem is that the eventual size of the network is huge despite a common scene recognition task has up to a few tens of scene categories. Thus, the goal is to ascertain possibility of a size reduction. The modelling recognition task is a small dataset of 4485 grayscale images broken into 15 image categories. The pretrained network is AlexNet dealing with much simpler image categories whose number is 1000, though. This network has two fully connected layers, which can be potentially reduced or deleted. A regular transfer learning network occupies about 202.6 MB performing at up to 92 % accuracy rate for the scene recognition. It is revealed that deleting the layers is not reasonable. The network size is reduced by setting a fewer number of filters in the 17th and 20th layers of the AlexNet-based networks using a dichotomy principle or similar. The best truncated network with 384 and 192 filters in those layers performs at 93.3 % accuracy rate, and its size is 21.63 MB.

show abstract

Section: Discussionmentioning

confidence: 99%

An Efficient Technique for Size Reduction of Convolutional Neural Networks after Transfer Learning for Scene Recognition Tasks

Romanuke

2018

Applied Computer Systems

View full text Add to dashboard Cite

show abstract

An Iterative Transfer Learning based Classification framework

Cited by 1 publication

References 42 publications

An Efficient Technique for Size Reduction of Convolutional Neural Networks after Transfer Learning for Scene Recognition Tasks

An Efficient Technique for Size Reduction of Convolutional Neural Networks after Transfer Learning for Scene Recognition Tasks

Contact Info

Product

Resources

About