# SAC-ViT: Semantic-Aware Clustering Vision Transformer with Early Exit

arXiv: https://arxiv.org/abs/2503.00060 · HTML: https://mlsanity.com/paper/2503.00060/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 45 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## Builds on (most cited first, 30 of 37)

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows](https://mlsanity.com/paper/2107.00652/) (2021)
- [Conditional Positional Encodings for Vision Transformers](https://mlsanity.com/paper/2102.10882/) (2021)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)
- [CMT: Convolutional Neural Networks Meet Vision Transformers](https://mlsanity.com/paper/2107.06263/) (2021)
- [Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer](https://mlsanity.com/paper/2108.01390/) (2021)
- [IA-RED2: Interpretability-Aware Redundancy Reduction for Vision Transformers](https://mlsanity.com/paper/2106.12620/) (2021)
- [Attentional Feature Fusion](https://mlsanity.com/paper/2009.14082/) (2020)
- [Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity](https://mlsanity.com/paper/2111.14330/) (2021)
- [AI Benchmark: All About Deep Learning on Smartphones in 2019](https://mlsanity.com/paper/1910.06663/) (2019)
- [FasterViT: Fast Vision Transformers with Hierarchical Attention](https://mlsanity.com/paper/2306.06189/) (2023)
- [CF-ViT: A General Coarse-to-Fine Method for Vision Transformer](https://mlsanity.com/paper/2203.03821/) (2022)
- [SpectFormer: Frequency and Attention is what you need in a Vision Transformer](https://mlsanity.com/paper/2304.06446/) (2023)
- [SG-Former: Self-guided Transformer with Evolving Token Reallocation](https://mlsanity.com/paper/2308.12216/) (2023)

## Built on by (most cited first, 1 of 1)

- [A Synthetic-to-Real Dehazing Method based on Domain Unification](https://mlsanity.com/paper/2509.05374/) (2025)

## Abstract (arXiv)

The Vision Transformer (ViT) excels in global modeling but faces deployment challenges on resource-constrained devices due to the quadratic computational complexity of its attention mechanism. To address this, we propose the Semantic-Aware Clustering Vision Transformer (SAC-ViT), a non-iterative approach to enhance ViT's computational efficiency. SAC-ViT operates in two stages: Early Exit (EE) and Semantic-Aware Clustering (SAC). In the EE stage, downsampled input images are processed to extract global semantic information and generate initial inference results. If these results do not meet the EE termination criteria, the information is clustered into target and non-target tokens. In the SAC stage, target tokens are mapped back to the original image, cropped, and embedded. These target tokens are then combined with reused non-target tokens from the EE stage, and the attention mechanism is applied within each cluster. This two-stage design, with end-to-end optimization, reduces spatial redundancy and enhances computational efficiency, significantly boosting overall ViT performance. Extensive experiments demonstrate the efficacy of SAC-ViT, reducing 62% of the FLOPs of DeiT and achieving 1.98 times throughput without compromising performance.