Volume- 8
Issue- 6
Year- 2020
DOI: 10.21276/ijircst.2020.8.6.8 |
DOI URL: https://doi.org/10.21276/ijircst.2020.8.6.8
Crossref
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0) (http://creativecommons.org/licenses/by/4.0)
Article Tools: Print the Abstract | Indexing metadata | How to cite item | Email this article | Post a Comment
Praveen Kumar , Rishabh Singh, Nilesh Kumar Singh, Hitesh Agarwal
Deep neural networks have attained almost human-level performance over several Image classification and object detection problems, deploying robust and powerful state-of-the-art networks. Stanford’s Tiny ImageNet dataset has been around for a while and neural networks have struggled to classify them. It is generally considered one of the harder datasets in the domain of image classification. The validation accuracy of the existing systems maxes out at 61- 62% with a select few shooting beyond 68-69%. These approaches are often plagued by problems of overfitting and vanishing gradients. In this paper, we present a new method to get above average validation accuracy while circumventing these problems. We use the resizing image technique which trains multiple model times over different image sizes. This approach enables the model to derive more relevant and precise features as we move towards the original image size. It also makes the training process adaptable to available hardware resources. After reaching the image size, we hyper-tune other parameters such as Learning Rate, Optimizers, etc. to increase the overall validation accuracy. The final validation accuracy of the model using resizing and hyper tuning is 62.57%.
[1] Z. Abai, N. Rajmalwar, et al., “DenseNet Models for Tiny ImageNet Classification,” arXiv:1904.10429 [cs.CV].
[2] S. F. L. Shi, “Kaminet - a convolutional neural network for tiny imagenet challenge,” CS, vol. 231, 2015.
[3] A. S. Walia, “The Vanishing Gradient Problem.” [Online]. Available: https://medium.com/
[4] “What is the Exploding Gradient Problem?” [Online]. Avail- able: https://deepai.org/machine-learning-glossary-and-terms/exploding- gradient-problem
[5] L. N. Smith, “Nicholay Topin. Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates,” arXiv:1708.07120 [cs.LG].
[6] S. Hochreiter, “ The vanishing gradient problem during learning recurrent neural nets and problem solutions,” International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, vol. 2, no. 107–116, 1998. [Online]. Available: https://www.bioinf.jku.at/publications/older/2304.pdf
[7] Google, “TensorFlow playground .” [Online]. Available: https:// playground.tensorflow.org/
[8] L N. Smith, “Cyclic Learning rates for training neural networks”, arXiv:1506.01186[cs.CV]
[9] Abinav Shrivastava, Abhinav Gupta, Ross Girshick,” Training region-based object detectors with online hard example mining”, arXiv:1604.03540 [sc.CV]
[10] ILSVRC, “https://tiny-imagenet.herokuapp.com/”
[11] Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov,” Dropout: a simple way to prevent neural networks from overfitting”, journal of machine learning research 15 (2014)
[12]Jarek Duda, “SGD momentum optimizer with step estimation by online parabola model”, arXiv:1907.07063 [cs.LG]
Student, Department of Computer Science & Engineering, MVJ College of Engineering, Whitefield, Bangalore, India (email: inboxpraveenkumar17@gmail.com)
No. of Downloads: 59 | No. of Views: 1694
Lingxi Xiao, Ruilin Xu, Yiru Cang, Yan Chen, Yijing Wei.
May 2024 - Vol 12, Issue 3
Anuj Kumar Kem, Ayush Chauhan, Mohan Agnihotri, Aniruddh Kumar.
May 2024 - Vol 12, Issue 3
Pravek Sharma, Dr. Rajesh Tyagi, Dr. Priyanka Dubey.
May 2024 - Vol 12, Issue 3