# CNN and ViT Efficiency Study on Tiny ImageNet and DermaMNIST Datasets

arXiv: https://arxiv.org/abs/2505.08259 · HTML: https://mlsanity.com/paper/2505.08259/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 13 May 2025.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [Vision Transformer for Small-Size Datasets](https://mlsanity.com/paper/2112.13492/) (2021)
- [Vision Transformers in 2022: An Update on Tiny ImageNet](https://mlsanity.com/paper/2205.10660/) (2022)
- [Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasets](https://mlsanity.com/paper/2401.14497/) (2024)
- [Lightweight Deep Models for Dermatological Disease Detection: A Study on Instance Selection and Channel Optimization](https://mlsanity.com/paper/2504.01208/) (2025)

## Built on by (most cited first, 4 of 4)

- [An Explorative Analysis of SVM Classifier and ResNet50 Architecture on African Food Classification](https://mlsanity.com/paper/2505.13923/) (2025)
- [DOME: Improving Signal-to-Noise in Stochastic Gradient Descent via Sharp-Direction Subspace Filtering](https://mlsanity.com/paper/2507.03545/) (2025)
- [BioAutoML-NAS: An End-to-End AutoML Framework for Multimodal Insect Classification via Neural Architecture Search on Large-Scale Biodiversity Data](https://mlsanity.com/paper/2510.05888/) (2025)
- [an interpretable vision transformer framework for automated brain tumor classification](https://mlsanity.com/paper/2604.21311/) (2026)

## Abstract (arXiv)

This study evaluates the trade-offs between convolutional and transformer-based architectures on both medical and general-purpose image classification benchmarks. We use ResNet-18 as our baseline and introduce a fine-tuning strategy applied to four Vision Transformer variants (Tiny, Small, Base, Large) on DermatologyMNIST and TinyImageNet. Our goal is to reduce inference latency and model complexity with acceptable accuracy degradation. Through systematic hyperparameter variations, we demonstrate that appropriately fine-tuned Vision Transformers can match or exceed the baseline's performance, achieve faster inference, and operate with fewer parameters, highlighting their viability for deployment in resource-constrained environments.