Vision Transformers for Image Classification using Convolution Neural Network (CNN)

NAGA VENKATA SAI LAKSHMI DEVI KOTTAGUNDA; NELAKUDITI LAKSHMI PRASANNA SAI; MAJJARI MAHESHWARI; MOHITHA GUNDAVARAPU

Vision Transformers for Image Classification using Convolution Neural Network (CNN)

May 2022

Vol-8, Issue-3

Paper ID: 16926

ISSN: 2395-4396

Downloads: 0

Abstract & Details

Research Area

Electronics and Communication Engineering

Keywords

Image classification convolution neural networks vision transformers mobile-vision transformers Inductive bias spatial dimensions

Abstract

Convolution Neural Networks (CNNs) are de-facto for computer vision applications. CNNs learn spatially local representations across different vision tasks based on their inductive biases. Further improvement in the performance can be achieved by learning global representations which require self-attention-based vision transformers (ViT’s). However, this improvement is obtained only at the cost of ViT’s being heavy-weight unlike CNNs. In this project we investigate the possibilities of building a model which is both light-weight and having low latency that are suitable for deploying on edge computing devices such as mobiles. We are planning to train and test our network on different image datasets such as Image Net that are available in public domains.

License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Author Information

#	Name	Institute / Affiliation
1	NAGA VENKATA SAI LAKSHMI DEVI KOTTAGUNDA	VASIREDDY VENKATADRI INSTITUTE OF TECHNOLOGY
2	NELAKUDITI LAKSHMI PRASANNA SAI	VASIREDDY VENKATADRI INSTITUTE OF TECHNOLOGY
3	MAJJARI MAHESHWARI	VASIREDDY VENKATADRI INSTITUTE OF TECHNOLOGY
4	MOHITHA GUNDAVARAPU	VASIREDDY VENKATADRI INSTITUTE OF TECHNOLOGY

How to Cite

Use the following formats to cite this article in your research.

APA Style

KOTTAGUNDA, NAGA VENKATA SAI LAKSHMI DEVI, SAI, NELAKUDITI LAKSHMI PRASANNA, MAHESHWARI, MAJJARI, & GUNDAVARAPU, MOHITHA (2022). Vision Transformers for Image Classification using Convolution Neural Network (CNN). International Journal of Advance Research and Innovative Ideas In Education, 8(3), 2044-2048.

MLA Style

KOTTAGUNDA, NAGA VENKATA SAI LAKSHMI DEVI, et al. "Vision Transformers for Image Classification using Convolution Neural Network (CNN)." International Journal of Advance Research and Innovative Ideas In Education, vol. 8, no. 3, 2022, pp. 2044-2048.

IEEE Style

NAGA VENKATA SAI LAKSHMI DEVI KOTTAGUNDA, NELAKUDITI LAKSHMI PRASANNA SAI, MAJJARI MAHESHWARI, and MOHITHA GUNDAVARAPU, "Vision Transformers for Image Classification using Convolution Neural Network (CNN)," International Journal of Advance Research and Innovative Ideas In Education, vol. 8, no. 3, pp. 2044-2048, 2022.

Vancouver Style

KOTTAGUNDA NAGA VENKATA SAI LAKSHMI DEVI, SAI NELAKUDITI LAKSHMI PRASANNA, MAHESHWARI MAJJARI, GUNDAVARAPU MOHITHA. Vision Transformers for Image Classification using Convolution Neural Network (CNN). International Journal of Advance Research and Innovative Ideas In Education. 2022;8(3):2044-2048.

Harvard Style

KOTTAGUNDA, NAGA VENKATA SAI LAKSHMI DEVI, SAI, NELAKUDITI LAKSHMI PRASANNA, MAHESHWARI, MAJJARI, & GUNDAVARAPU, MOHITHA (2022) 'Vision Transformers for Image Classification using Convolution Neural Network (CNN)', International Journal of Advance Research and Innovative Ideas In Education, 8(3), pp. 2044-2048.

Chicago Style

KOTTAGUNDA, NAGA VENKATA SAI LAKSHMI DEVI, et al. "Vision Transformers for Image Classification using Convolution Neural Network (CNN)." International Journal of Advance Research and Innovative Ideas In Education 8, no. 3 (2022): 2044-2048.

Turabian Style

KOTTAGUNDA, NAGA VENKATA SAI LAKSHMI DEVI, et al. "Vision Transformers for Image Classification using Convolution Neural Network (CNN)." International Journal of Advance Research and Innovative Ideas In Education 8, no. 3 (2022): 2044-2048.