# Convolutional Embedding Makes Hierarchical Vision Transformer Stronger

arXiv: https://arxiv.org/abs/2207.13317 · HTML: https://mlsanity.com/paper/2207.13317/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 71 of its 79 references that are in the map.
- First posted on arXiv 27 Jul 2022.

## Builds on (most cited first, 30 of 71)

- [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)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [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)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [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)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [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)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)

## Built on by (most cited first, 10 of 10)

- [Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation](https://mlsanity.com/paper/2303.00440/) (2023)
- [SG-Former: Self-guided Transformer with Evolving Token Reallocation](https://mlsanity.com/paper/2308.12216/) (2023)
- [Dual Cross-Attention for Medical Image Segmentation](https://mlsanity.com/paper/2303.17696/) (2023)
- [Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey](https://mlsanity.com/paper/2402.02941/) (2024)
- [HSViT: Horizontally Scalable Vision Transformer](https://mlsanity.com/paper/2404.05196/) (2024)
- [Merging Context Clustering with Visual State Space Models for Medical Image Segmentation](https://mlsanity.com/paper/2501.01618/) (2025)
- [EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention](https://mlsanity.com/paper/2310.06629/) (2023)
- [MAProtoNet: A Multi-scale Attentive Interpretable Prototypical Part Network for 3D Magnetic Resonance Imaging Brain Tumor Classification](https://mlsanity.com/paper/2404.08917/) (2024)
- [Token Transformer: Can class token help window-based transformer build better long-range interactions?](https://mlsanity.com/paper/2211.06083/) (2022)
- [A unified framework for geometry-independent operator learning in cardiac electrophysiology simulations](https://mlsanity.com/paper/2512.01702/) (2025)

## Abstract (arXiv)

Vision Transformers (ViTs) have recently dominated a range of computer vision tasks, yet it suffers from low training data efficiency and inferior local semantic representation capability without appropriate inductive bias. Convolutional neural networks (CNNs) inherently capture regional-aware semantics, inspiring researchers to introduce CNNs back into the architecture of the ViTs to provide desirable inductive bias for ViTs. However, is the locality achieved by the micro-level CNNs embedded in ViTs good enough? In this paper, we investigate the problem by profoundly exploring how the macro architecture of the hybrid CNNs/ViTs enhances the performances of hierarchical ViTs. Particularly, we study the role of token embedding layers, alias convolutional embedding (CE), and systemically reveal how CE injects desirable inductive bias in ViTs. Besides, we apply the optimal CE configuration to 4 recently released state-of-the-art ViTs, effectively boosting the corresponding performances. Finally, a family of efficient hybrid CNNs/ViTs, dubbed CETNets, are released, which may serve as generic vision backbones. Specifically, CETNets achieve 84.9% Top-1 accuracy on ImageNet-1K (training from scratch), 48.6% box mAP on the COCO benchmark, and 51.6% mIoU on the ADE20K, substantially improving the performances of the corresponding state-of-the-art baselines.