Convolutional Neural Networks and Vision Transformers for Fashion MNIST Classification: A Literature Review
Not on the map. Why?
Abstract (arXiv)
Our review explores the comparative analysis between Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) in the domain of image classification, with a particular focus on clothing classification within the e-commerce sector. Utilizing the Fashion MNIST dataset, we delve into the unique attributes of CNNs and ViTs. While CNNs have long been the cornerstone of image classification, ViTs introduce an innovative self-attention mechanism enabling nuanced weighting of different input data components. Historically, transformers have primarily been associated with Natural Language Processing (NLP) tasks. Through a comprehensive examination of existing literature, our aim is to unveil the distinctions between ViTs and CNNs in the context of image classification. Our analysis meticulously scrutinizes state-of-the-art methodologies employing both architectures, striving to identify the factors influencing their performance. These factors encompass dataset characteristics, image dimensions, the number of target classes, hardware infrastructure, and the specific architectures along with their respective top results. Our key goal is to determine the most appropriate architecture between ViT and CNN for classifying images in the Fashion MNIST dataset within the e-commerce industry, while taking into account specific conditions and needs. We highlight the importance of combining these two architectures with different forms to enhance overall performance. By uniting these architectures, we can take advantage of their unique strengths, which may lead to more precise and reliable models for e-commerce applications. CNNs are skilled at recognizing local patterns, while ViTs are effective at grasping overall context, making their combination a promising strategy for boosting image classification performance.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 39 of its 106 references that are in the map. First posted on arXiv 5 Jun 2024.
Builds on
39 of 106 references.
References · 39
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
- 2021Transformers in Vision: A Surveycited by 1,009
- 2021Scaling Vision Transformerscited by 993
- 2021Segmenter: Transformer for Semantic Segmentationcited by 855
- 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
- 2021Going deeper with Image Transformerscited by 759
27 more
- 2021Transformer in Transformercited by 632
- 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 566
- 2021ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescited by 484
- 2022DeiT III: Revenge of the ViTcited by 417
- 2021AdaViT: Adaptive Tokens for Efficient Vision Transformercited by 360
- 2021Post-Training Quantization for Vision Transformercited by 274
- 2021Conformer: Local Features Coupling Global Representations for Visual Recognitioncited by 164
- 2021Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challengescited by 143
- 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
- 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
- 2021A Survey of Visual Transformerscited by 117
- 2021LambdaNetworks: Modeling Long-Range Interactions Without Attentioncited by 107
- 2018Learning long-range spatial dependencies with horizontal gated-recurrent unitscited by 98
- 2022Dilated Neighborhood Attention Transformercited by 64
- 2019Squeeze-and-Attention Networks for Semantic Segmentationcited by 60
- 2024A Survey on Transformer Compressioncited by 44
- 2023NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Imagescited by 32
- 2023Analyzing Vision Transformers for Image Classification in Class Embedding Spacecited by 26
- 2022A Review of Modern Fashion Recommender Systemscited by 25
- 2022A comparative study between vision transformers and CNNs in digital pathologycited by 16
- 2022A Comprehensive Survey of Transformers for Computer Visioncited by 13
- 2024Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A surveycited by 13
- 2024HSViT: Horizontally Scalable Vision Transformercited by 6
- 2021An Efficient Style Virtual Try on Network for Clothing Business Industrycited by 2
- 2022Deep learning and machine learning for Malaria detection: overview, challenges and future directionscited by 2
- 2022PatchRot: A Self-Supervised Technique for Training Vision Transformerscited by 2
- 2023Element-Wise Attention Layers: an option for optimizationcited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.