Resizing Tiny Imagenet: An Iterative Approach Towards Image Classification
Keywords:
Tiny ImageNet, Residual Networks, Classification, ILSVRC, Deep ArchitecturesAbstract
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%.
Downloads
References
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.
A. S. Walia, “The Vanishing Gradient Problem.” [Online]. Available: https://medium.com/
“What is the Exploding Gradient Problem?” [Online]. Avail- able: https://deepai.org/machine learning-glossary-and-terms/exploding- gradient-problem
L. N. Smith, “Nicholay Topin. Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates,” arXiv:1708.07120 [cs.LG].
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
Google, “TensorFlow playground .” [Online]. Available: https:// playground.tensorflow.org/
L N. Smith, “Cyclic Learning rates for training neural networks”, arXiv:1506.01186[cs.CV]
Abinav Shrivastava, Abhinav Gupta, Ross Girshick,” Training region-based object detectors with online hard example mining”, arXiv:1604.03540 [sc.CV]
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)
Jarek Duda, “SGD momentum optimizer with step estimation by online parabola model”, arXiv:1907.07063 [cs.LG]
