# SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer

arXiv: https://arxiv.org/abs/2303.17605 · HTML: https://mlsanity.com/paper/2303.17605/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 63 references that are in the map.
- First posted on arXiv 30 Mar 2023.

## Builds on (most cited first, 30 of 54)

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)

## Built on by (most cited first, 30 of 60)

- [PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation](https://mlsanity.com/paper/2403.04692/) (2024)
- [Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement](https://mlsanity.com/paper/2310.00227/) (2023)
- [Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation](https://mlsanity.com/paper/2308.01045/) (2023)
- [Training-Free Activation Sparsity in Large Language Models](https://mlsanity.com/paper/2408.14690/) (2024)
- [Revisiting Token Pruning for Object Detection and Instance Segmentation](https://mlsanity.com/paper/2306.07050/) (2023)
- [Scene Adaptive Sparse Transformer for Event-based Object Detection](https://mlsanity.com/paper/2404.01882/) (2024)
- [HRVDA: High-Resolution Visual Document Assistant](https://mlsanity.com/paper/2404.06918/) (2024)
- [Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKV](https://mlsanity.com/paper/2407.11087/) (2024)
- [Scaling Vision Pre-Training to 4K Resolution](https://mlsanity.com/paper/2503.19903/) (2025)
- [Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion](https://mlsanity.com/paper/2310.04361/) (2023)
- [SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference](https://mlsanity.com/paper/2510.17777/) (2025)
- [Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation](https://mlsanity.com/paper/2407.17261/) (2024)
- [Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy](https://mlsanity.com/paper/2410.09873/) (2024)
- [Agglomerative Token Clustering](https://mlsanity.com/paper/2409.11923/) (2024)
- [Accelerating Vision Transformers with Adaptive Patch Sizes](https://mlsanity.com/paper/2510.18091/) (2025)
- [Win-Win: Training High-Resolution Vision Transformers from Two Windows](https://mlsanity.com/paper/2310.00632/) (2023)
- [Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference](https://mlsanity.com/paper/2405.14700/) (2024)
- [iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models](https://mlsanity.com/paper/2412.06263/) (2024)
- [Conditional computation in neural networks: principles and research trends](https://mlsanity.com/paper/2403.07965/) (2024)
- [Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation](https://mlsanity.com/paper/2405.16486/) (2024)
- [Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers](https://mlsanity.com/paper/2511.14751/) (2025)
- [HTTM: Head-wise Temporal Token Merging for Faster VGGT](https://mlsanity.com/paper/2511.21317/) (2025)
- [RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy](https://mlsanity.com/paper/2505.21036/) (2025)
- [LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression](https://mlsanity.com/paper/2509.00419/) (2025)
- [La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation](https://mlsanity.com/paper/2507.01299/) (2025)
- [MaskVD: Region Masking for Efficient Video Object Detection](https://mlsanity.com/paper/2407.12067/) (2024)
- [PAR: Prompt-Aware Token Reduction Method for Efficient Large Multimodal Models](https://mlsanity.com/paper/2410.07278/) (2024)
- [A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion](https://mlsanity.com/paper/2501.07451/) (2025)
- [IPCV: Information-Preserving Compression for MLLM Visual Encoders](https://mlsanity.com/paper/2512.18747/) (2025)
- [SparseSwin: Swin Transformer with Sparse Transformer Block](https://mlsanity.com/paper/2309.05224/) (2023)

## Abstract (arXiv)

High-resolution images enable neural networks to learn richer visual representations. However, this improved performance comes at the cost of growing computational complexity, hindering their usage in latency-sensitive applications. As not all pixels are equal, skipping computations for less-important regions offers a simple and effective measure to reduce the computation. This, however, is hard to be translated into actual speedup for CNNs since it breaks the regularity of the dense convolution workload. In this paper, we introduce SparseViT that revisits activation sparsity for recent window-based vision transformers (ViTs). As window attentions are naturally batched over blocks, actual speedup with window activation pruning becomes possible: i.e., ~50% latency reduction with 60% sparsity. Different layers should be assigned with different pruning ratios due to their diverse sensitivities and computational costs. We introduce sparsity-aware adaptation and apply the evolutionary search to efficiently find the optimal layerwise sparsity configuration within the vast search space. SparseViT achieves speedups of 1.5x, 1.4x, and 1.3x compared to its dense counterpart in monocular 3D object detection, 2D instance segmentation, and 2D semantic segmentation, respectively, with negligible to no loss of accuracy.