Computationally Efficient Approaches for Image Style Transfer

Pandey, RK and Karmakar, S and Ramakrishnan, AG (2020) Computationally Efficient Approaches for Image Style Transfer. In: 2018 15th IEEE India Council International Conference (INDICON), 16-18 Dec. 2018, Coimbatore, India.

PDF Com_Eff_App_Img_Dec_2018.pdf - Published Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

In this work, our focus is on developing fast image style transfer architectures for practical applications. We have proposed three modifications to the architecture of a recent, real-time, artistic style transfer technique to make it computationally more efficient. We have proposed the use of depth-wise separable convolution (DepSep) in place of convolution and nearest neighbor (NN) interpolation in place of transposed convolution. We have also explored the concatenation of nearest neighbour and bilinear (Bil) interpolations in place of transposed convolution. The stylized images from the modified architectures are perceptually similar in quality to those from the original architecture. The decrease in the computational complexity of our architectures is validated by the decrease in the testing time by 26.1, 39.1, and 57.1, respectively, for DepSep, DepSep-NN-Bil and DepSep-NN modifications. Working with another architecture, we have examined how the quality of the stylized reconstruction changes with the change of the loss function to be minimized.

Item Type:	Conference Paper
Publication:	INDICON 2018 - 15th IEEE India Council International Conference
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	cited By 0; Conference of 15th IEEE India Council International Conference, INDICON 2018 ; Conference Date: 16 December 2018 Through 18 December 2018; Conference Code:158392
Keywords:	Computational complexity; Interpolation, Artistic style transfer; Computationally efficient; Image style transfer; Modified architecture; Nearest neighbor interpolation; Nearest neighbors; Nearest neighbour; Separable representations, Convolution
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	22 Sep 2020 06:05
Last Modified:	22 Sep 2020 06:05
URI:	http://eprints.iisc.ac.in/id/eprint/65147

Actions (login required)

View Item