Resizing Tiny Imagenet: An Iterative Approach Towards Image Classification
Journal Title: International Journal of Innovative Research in Computer Science and Technology - Year 2020, Vol 8, Issue 6
Abstract
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%.
Authors and Affiliations
Praveen Kumar, Rishabh Singh, Nilesh Kumar Singh, Hitesh Agarwal
Keywords
Related Articles
- EP ID EP747612
- DOI 10.21276/ijircst.2020.8.6.8
- Views 40
- Downloads 0
Better Defect Analysis and Defect Prevention for Software Process Quality Improvement
Most large software products have good quality control process. Defect Prevention can be applied to one or more phases of the software development life cycle to improve software process quality. Defect Prevention involve...
Urgent Data Transmission in Wireless Sensor Network
Paper wireless sensor networks is a growing class of highly dynamic, complex network environment on top of which a wide range of applications, such as habitat monitoring, object tracking, precision agriculture, building...
Customer Churn Scrutiny and Prediction Using Data Extraction Models in Funding Sectors
A new method for customer churn analysis and prediction has been proposed. The method uses data Extraction model in Funding industries. This has been inspired by the fact that there are around 1,5 million churn customers...
A Brief Study on Face Expression Recognition System
The most significant type of expressive is body language. Nonverbal communication. Face expression recognition (FER) systems have been developed to serve real-world applications rather than laboratory settings, owing to...
CMRepo End-to-End Automation
Performance Automation is a technique which helps in determining the performance of the system, by determining various system parameters under different workloads. This project aims at developing the framework for determ...