# CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications

arXiv: https://arxiv.org/abs/2408.03703 · HTML: https://mlsanity.com/paper/2408.03703/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 69 of its 80 references that are in the map.
- First posted on arXiv 7 Aug 2024.

## Builds on (most cited first, 30 of 69)

- [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)
- [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)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [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)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)

## Built on by (most cited first, 12 of 12)

- [PolaFormer: Polarity-aware Linear Attention for Vision Transformers](https://mlsanity.com/paper/2501.15061/) (2025)
- [iFormer: Integrating ConvNet and Transformer for Mobile Application](https://mlsanity.com/paper/2501.15369/) (2025)
- [SRMamba: Mamba for Super-Resolution of LiDAR Point Clouds](https://mlsanity.com/paper/2505.10601/) (2025)
- [S2AFormer: Strip Self-Attention for Efficient Vision Transformer](https://mlsanity.com/paper/2505.22195/) (2025)
- [EFA-YOLO: An Efficient Feature Attention Model for Fire and Flame Detection](https://mlsanity.com/paper/2409.12635/) (2024)
- [SRMambaV2: Biomimetic Attention for Sparse Point Cloud Upsampling in Autonomous Driving](https://mlsanity.com/paper/2507.17479/) (2025)
- [Neural Attention: A Novel Mechanism for Enhanced Expressive Power in Transformer Models](https://mlsanity.com/paper/2502.17206/) (2025)
- [YOLO-FireAD: Efficient Fire Detection via Attention-Guided Inverted Residual Learning and Dual-Pooling Feature Preservation](https://mlsanity.com/paper/2505.20884/) (2025)
- [Lightweight Backbone Networks Only Require Adaptive Lightweight Self-Attention Mechanisms](https://mlsanity.com/paper/2508.01385/) (2025)
- [A Spatial Semantics and Continuity Perception Attention for Remote Sensing Water Body Change Detection](https://mlsanity.com/paper/2511.16143/) (2025)
- [ReGLA: Efficient Receptive-Field Modeling with Gated Linear Attention Network](https://mlsanity.com/paper/2602.05262/) (2026)
- [UtVAA: Ultra-tiny Vision Transformer with Affix Attention for Mobile Image Classification](https://mlsanity.com/paper/2606.14735/) (2026)

## Abstract (arXiv)

Vision Transformers (ViTs) mark a revolutionary advance in neural networks with their token mixer's powerful global context capability. However, the pairwise token affinity and complex matrix operations limit its deployment on resource-constrained scenarios and real-time applications, such as mobile devices, although considerable efforts have been made in previous works. In this paper, we introduce CAS-ViT: Convolutional Additive Self-attention Vision Transformers, to achieve a balance between efficiency and performance in mobile applications. Firstly, we argue that the capability of token mixers to obtain global contextual information hinges on multiple information interactions, such as spatial and channel domains. Subsequently, we propose Convolutional Additive Token Mixer (CATM) employing underlying spatial and channel attention as novel interaction forms. This module eliminates troublesome complex operations such as matrix multiplication and Softmax. We introduce Convolutional Additive Self-attention(CAS) block hybrid architecture and utilize CATM for each block. And further, we build a family of lightweight networks, which can be easily extended to various downstream tasks. Finally, we evaluate CAS-ViT across a variety of vision tasks, including image classification, object detection, instance segmentation, and semantic segmentation. Our M and T model achieves 83.0%/84.1% top-1 with only 12M/21M parameters on ImageNet-1K. Meanwhile, throughput evaluations on GPUs, ONNX, and iPhones also demonstrate superior results compared to other state-of-the-art backbones. Extensive experiments demonstrate that our approach achieves a better balance of performance, efficient inference and easy-to-deploy. Our code and model are available at: urlhttps://github.com/Tianfang-Zhang/CAS-ViT