# TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition

arXiv: https://arxiv.org/abs/2310.19380 · HTML: https://mlsanity.com/paper/2310.19380/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 59 of its 67 references that are in the map.
- First posted on arXiv 30 Oct 2023.

## Builds on (most cited first, 30 of 59)

- [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)
- [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)
- [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)
- [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)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [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)
- [CoAtNet: Marrying Convolution and Attention for All Data Sizes](https://mlsanity.com/paper/2106.04803/) (2021)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows](https://mlsanity.com/paper/2107.00652/) (2021)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [Conditional Positional Encodings for Vision Transformers](https://mlsanity.com/paper/2102.10882/) (2021)
- [Early Convolutions Help Transformers See Better](https://mlsanity.com/paper/2106.14881/) (2021)
- [ResNet strikes back: An improved training procedure in timm](https://mlsanity.com/paper/2110.00476/) (2021)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)

## Built on by (most cited first, 21 of 21)

- [SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation](https://mlsanity.com/paper/2412.11890/) (2024)
- [OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels](https://mlsanity.com/paper/2502.20087/) (2025)
- [Vision Transformers Need More Than Registers](https://mlsanity.com/paper/2602.22394/) (2026)
- [D-Net: Dynamic Large Kernel with Dynamic Feature Fusion for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/2403.10674/) (2024)
- [SVIPTR: Fast and Efficient Scene Text Recognition with Vision Permutable Extractor](https://mlsanity.com/paper/2401.10110/) (2024)
- [Image Demoir'eing Using Dual Camera Fusion on Mobile Phones](https://mlsanity.com/paper/2506.08361/) (2025)
- [Vision Transformers are Circulant Attention Learners](https://mlsanity.com/paper/2512.21542/) (2025)
- [Optimizing Local-Global Dependencies for Accurate 3D Human Pose Estimation](https://mlsanity.com/paper/2412.19676/) (2024)
- [FourierSR: A Fourier Token-based Plugin for Efficient Image Super-Resolution](https://mlsanity.com/paper/2503.10043/) (2025)
- [A2Mamba: Attention-augmented State Space Models for Visual Recognition](https://mlsanity.com/paper/2507.16624/) (2025)
- [Parameters as Experts: Adapting Vision Models with Dynamic Parameter Routing](https://mlsanity.com/paper/2602.06862/) (2026)
- [CVGL: Causal Learning and Geometric Topology](https://mlsanity.com/paper/2603.12551/) (2026)
- [One Pixel is All I Need](https://mlsanity.com/paper/2412.10681/) (2024)
- [VRS-UIE: Value-Driven Reordering Scanning for Underwater Image Enhancement](https://mlsanity.com/paper/2505.01224/) (2025)
- [IONext: Unlocking the Next Era of Inertial Odometry](https://mlsanity.com/paper/2507.17089/) (2025)
- [WaveSeg: Enhancing Segmentation Precision via High-Frequency Prior and Mamba-Driven Spectrum Decomposition](https://mlsanity.com/paper/2510.21079/) (2025)
- [CLAReSNet: When Convolution Meets Latent Attention for Hyperspectral Image Classification](https://mlsanity.com/paper/2511.12346/) (2025)
- [PestVL-Net: Enabling Multimodal Pest Learning via Fine-grained Vision-Language Interaction](https://mlsanity.com/paper/2604.17278/) (2026)
- [BMCR: Adaptive Backbone Module Composition via Reinforcement Learning for Remote Sensing Object Detection](https://mlsanity.com/paper/2606.05586/) (2026)
- [CLARE: Scalable Class-Incremental Continual Learning via a Sparsity-Based Framework](https://mlsanity.com/paper/2609.17026/) (2026)
- [M3D-Net: Hierarchical Coordination of Spatial Context, Feature Reuse, and Differential Attention for Mammography Classification](https://mlsanity.com/paper/2609.27523/) (2026)

## Abstract (arXiv)

Recent studies have integrated convolutions into transformers to introduce inductive bias and improve generalization performance. However, the static nature of conventional convolution prevents it from dynamically adapting to input variations, resulting in a representation discrepancy between convolution and self-attention as the latter computes attention maps dynamically. Furthermore, when stacking token mixers that consist of convolution and self-attention to form a deep network, the static nature of convolution hinders the fusion of features previously generated by self-attention into convolution kernels. These two limitations result in a sub-optimal representation capacity of the entire network. To find a solution, we propose a lightweight Dual Dynamic Token Mixer (D-Mixer) to simultaneously learn global and local dynamics via computing input-dependent global and local aggregation weights. D-Mixer works by applying an efficient global attention module and an input-dependent depthwise convolution separately on evenly split feature segments, endowing the network with strong inductive bias and an enlarged receptive field. We use D-Mixer as the basic building block to design TransXNet, a novel hybrid CNN-Transformer vision backbone network that delivers compelling performance. In the ImageNet-1K classification, TransXNet-T surpasses Swin-T by 0.3% in top-1 accuracy while requiring less than half of the computational cost. Furthermore, TransXNet-S and TransXNet-B exhibit excellent model scalability, achieving top-1 accuracy of 83.8% and 84.6% respectively, with reasonable computational costs. Additionally, our proposed network architecture demonstrates strong generalization capabilities in various dense prediction tasks, outperforming other state-of-the-art networks while having lower computational costs. Code is publicly available at https://github.com/LMMMEng/TransXNet.