# TinyViT: Fast Pretraining Distillation for Small Vision Transformers

arXiv: https://arxiv.org/abs/2207.10666 · HTML: https://mlsanity.com/paper/2207.10666/

## Key facts

- Cited by 234 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 84 references that are in the map.
- First posted on arXiv 21 Jul 2022.

## Builds on (most cited first, 30 of 68)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)

## Built on by (most cited first, 30 of 234)

- [Faster Segment Anything: Towards Lightweight SAM for Mobile Applications](https://mlsanity.com/paper/2306.14289/) (2023)
- [EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything](https://mlsanity.com/paper/2312.00863/) (2023)
- [EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention](https://mlsanity.com/paper/2305.07027/) (2023)
- [Logit Standardization in Knowledge Distillation](https://mlsanity.com/paper/2403.01427/) (2024)
- [Efficient Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2405.10739/) (2024)
- [TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance](https://mlsanity.com/paper/2309.12314/) (2023)
- [DiffRate : Differentiable Compression Rate for Efficient Vision Transformers](https://mlsanity.com/paper/2305.17997/) (2023)
- [MogaNet: Multi-order Gated Aggregation Network](https://mlsanity.com/paper/2211.03295/) (2022)
- [A Survey on Transformer Compression](https://mlsanity.com/paper/2402.05964/) (2024)
- [PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers](https://mlsanity.com/paper/2209.05687/) (2022)
- [A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking](https://mlsanity.com/paper/2309.02031/) (2023)
- [EdgeSAM: Prompt-In-the-Loop Distillation for SAM](https://mlsanity.com/paper/2312.06660/) (2023)
- [Distilling Large Vision-Language Model with Out-of-Distribution Generalizability](https://mlsanity.com/paper/2307.03135/) (2023)
- [TinySAM: Pushing the Envelope for Efficient Segment Anything Model](https://mlsanity.com/paper/2312.13789/) (2023)
- [Robustness of SAM: Segment Anything Under Corruptions and Beyond](https://mlsanity.com/paper/2306.07713/) (2023)
- [CED: Consistent ensemble distillation for audio tagging](https://mlsanity.com/paper/2308.11957/) (2023)
- [Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP](https://mlsanity.com/paper/2310.00927/) (2023)
- [Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies](https://mlsanity.com/paper/2503.02891/) (2025)
- [Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction](https://mlsanity.com/paper/2407.06794/) (2024)
- [Learned Thresholds Token Merging and Pruning for Vision Transformers](https://mlsanity.com/paper/2307.10780/) (2023)
- [DAT++: Spatially Dynamic Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2309.01430/) (2023)
- [Spiking Vision Transformer with Saccadic Attention](https://mlsanity.com/paper/2502.12677/) (2025)
- [SlimSAM: 0.1% Data Makes Segment Anything Slim](https://mlsanity.com/paper/2312.05284/) (2023)
- [Generic-to-Specific Distillation of Masked Autoencoders](https://mlsanity.com/paper/2302.14771/) (2023)
- [DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers](https://mlsanity.com/paper/2408.03291/) (2024)
- [Learning-based Multi-View Stereo: A Survey](https://mlsanity.com/paper/2408.15235/) (2024)
- [RepViT-SAM: Towards Real-Time Segmenting Anything](https://mlsanity.com/paper/2312.05760/) (2023)
- [On Efficient Variants of Segment Anything Model: A Survey](https://mlsanity.com/paper/2410.04960/) (2024)
- [Accumulated Trivial Attention Matters in Vision Transformers on Small Datasets](https://mlsanity.com/paper/2210.12333/) (2022)
- [BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model](https://mlsanity.com/paper/2401.02317/) (2024)

## Abstract (arXiv)

Vision transformer (ViT) recently has drawn great attention in computer vision due to its remarkable model capability. However, most prevailing ViT models suffer from huge number of parameters, restricting their applicability on devices with limited resources. To alleviate this issue, we propose TinyViT, a new family of tiny and efficient small vision transformers pretrained on large-scale datasets with our proposed fast distillation framework. The central idea is to transfer knowledge from large pretrained models to small ones, while enabling small models to get the dividends of massive pretraining data. More specifically, we apply distillation during pretraining for knowledge transfer. The logits of large teacher models are sparsified and stored in disk in advance to save the memory cost and computation overheads. The tiny student transformers are automatically scaled down from a large pretrained model with computation and parameter constraints. Comprehensive experiments demonstrate the efficacy of TinyViT. It achieves a top-1 accuracy of 84.8% on ImageNet-1k with only 21M parameters, being comparable to Swin-B pretrained on ImageNet-21k while using 4.2 times fewer parameters. Moreover, increasing image resolutions, TinyViT can reach 86.5% accuracy, being slightly better than Swin-L while using only 11% parameters. Last but not the least, we demonstrate a good transfer ability of TinyViT on various downstream tasks. Code and models are available at https://github.com/microsoft/Cream/tree/main/TinyViT.