DenseNet Models for Tiny ImageNet Classification
Zoheb Abai, Nishad Rajmalwar
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/ZohebAbai/Tiny-ImageNet-ChallengeOfficialIn papernone★ 0
- github.com/2023-MindSpore-4/Code3/tree/main/densenetmindspore★ 0
- github.com/2023-MindSpore-1/ms-code-211/tree/main/densenetmindspore★ 0
Abstract
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| Tiny ImageNet Classification | DenseNet + Residual Networks | Validation Acc | 60 | — | Unverified |