DenseNet Models for Tiny ImageNet Classification
This work addresses image classification for the Tiny ImageNet dataset, but it is incremental as it applies existing DenseNet ideas with minor adaptations.
The authors tackled image classification on Tiny ImageNet by developing two DenseNet-based models from scratch, achieving a target top-1 validation accuracy of 60% under low computational resources.
In this paper, we present two image classification models on the Tiny ImageNet dataset. We built two very different networks from scratch based on the idea of Densely Connected Convolution Networks. The architecture of the networks is designed based on the image resolution of this specific dataset and by calculating the Receptive Field of the convolution layers. We also used some non-conventional techniques related to image augmentation and Cyclical Learning Rate to improve the accuracy of our models. The networks are trained under high constraints and low computation resources. We aimed to achieve top-1 validation accuracy of 60%; the results and error analysis are also presented.