# CAViT -- Channel-Aware Vision Transformer for Dynamic Feature Fusion

arXiv: https://arxiv.org/abs/2602.05598 · HTML: https://mlsanity.com/paper/2602.05598/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [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)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Pay Attention to MLPs](https://mlsanity.com/paper/2105.08050/) (2021)
- [XCiT: Cross-Covariance Image Transformers](https://mlsanity.com/paper/2106.09681/) (2021)
- [Transformers in Medical Imaging: A Survey](https://mlsanity.com/paper/2201.09873/) (2022)
- [An Introduction to Vision-Language Modeling](https://mlsanity.com/paper/2405.17247/) (2024)
- [DaViT: Dual Attention Vision Transformers](https://mlsanity.com/paper/2204.03645/) (2022)
- [Image Segmentation in Foundation Model Era: A Survey](https://mlsanity.com/paper/2408.12957/) (2024)
- [SWAT: Spatial Structure Within and Among Tokens](https://mlsanity.com/paper/2111.13677/) (2021)

## Abstract (arXiv)

Vision Transformers (ViTs) have demonstrated strong performance across a range of computer vision tasks by modeling long-range spatial interactions via self-attention. However, channel-wise mixing in ViTs remains static, relying on fixed multilayer perceptrons (MLPs) that lack adaptability to input content. We introduce 'CAViT', a dual-attention architecture that replaces the static MLP with a dynamic, attention-based mechanism for feature interaction. Each Transformer block in CAViT performs spatial self-attention followed by channel-wise self-attention, allowing the model to dynamically recalibrate feature representations based on global image context. This unified and content-aware token mixing strategy enhances representational expressiveness without increasing depth or complexity. We validate CAViT across five benchmark datasets spanning both natural and medical domains, where it outperforms the standard ViT baseline by up to +3.6% in accuracy, while reducing parameter count and FLOPs by over 30%. Qualitative attention maps reveal sharper and semantically meaningful activation patterns, validating the effectiveness of our attention-driven token mixing.