# Conformer: Local Features Coupling Global Representations for Visual Recognition

arXiv: https://arxiv.org/abs/2105.03889 · HTML: https://mlsanity.com/paper/2105.03889/

## Key facts

- Cited by 164 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 60 references that are in the map.
- First posted on arXiv 9 May 2021.

## Builds on (most cited first, 30 of 47)

- [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)
- [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)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [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)
- [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)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [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)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [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)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [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)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)

## Built on by (most cited first, 30 of 164)

- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Mobile-Former: Bridging MobileNet and Transformer](https://mlsanity.com/paper/2108.05895/) (2021)
- [ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias](https://mlsanity.com/paper/2106.03348/) (2021)
- [HRFormer: High-Resolution Transformer for Dense Prediction](https://mlsanity.com/paper/2110.09408/) (2021)
- [Dual Aggregation Transformer for Image Super-Resolution](https://mlsanity.com/paper/2308.03364/) (2023)
- [ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond](https://mlsanity.com/paper/2202.10108/) (2022)
- [CompletionFormer: Depth Completion with Convolutions and Vision Transformers](https://mlsanity.com/paper/2304.13030/) (2023)
- [On the Integration of Self-Attention and Convolution](https://mlsanity.com/paper/2111.14556/) (2021)
- [DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting](https://mlsanity.com/paper/2211.10772/) (2022)
- [A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks](https://mlsanity.com/paper/2306.07303/) (2023)
- [Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review](https://mlsanity.com/paper/2304.10410/) (2023)
- [A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization](https://mlsanity.com/paper/2201.09206/) (2022)
- [IEBins: Iterative Elastic Bins for Monocular Depth Estimation](https://mlsanity.com/paper/2309.14137/) (2023)
- [Deepfake Detection: A Comprehensive Survey from the Reliability Perspective](https://mlsanity.com/paper/2211.10881/) (2022)
- [Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?](https://mlsanity.com/paper/2203.08392/) (2022)
- [Neural Degradation Representation Learning for All-In-One Image Restoration](https://mlsanity.com/paper/2310.12848/) (2023)
- [MixFormer: Mixing Features across Windows and Dimensions](https://mlsanity.com/paper/2204.02557/) (2022)
- [Refiner: Refining Self-attention for Vision Transformers](https://mlsanity.com/paper/2106.03714/) (2021)
- [Xformer: Hybrid X-Shaped Transformer for Image Denoising](https://mlsanity.com/paper/2303.06440/) (2023)
- [HRDFuse: Monocular 360degDepth Estimation by Collaboratively Learning Holistic-with-Regional Depth Distributions](https://mlsanity.com/paper/2303.11616/) (2023)
- [Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention](https://mlsanity.com/paper/2112.14000/) (2021)
- [DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition](https://mlsanity.com/paper/2302.01791/) (2023)
- [Dual-stream Network for Visual Recognition](https://mlsanity.com/paper/2105.14734/) (2021)
- [Expression Snippet Transformer for Robust Video-based Facial Expression Recognition](https://mlsanity.com/paper/2109.08409/) (2021)
- [Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives](https://mlsanity.com/paper/2206.01136/) (2022)
- [Locality Guidance for Improving Vision Transformers on Tiny Datasets](https://mlsanity.com/paper/2207.10026/) (2022)
- [HiFuse: Hierarchical Multi-Scale Feature Fusion Network for Medical Image Classification](https://mlsanity.com/paper/2209.10218/) (2022)
- [Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small Datasets](https://mlsanity.com/paper/2210.05958/) (2022)
- [TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.07239/) (2022)
- [Lightweight Vision Transformer with Bidirectional Interaction](https://mlsanity.com/paper/2306.00396/) (2023)

## Abstract (arXiv)

Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations. Within visual transformer, the cascaded self-attention modules can capture long-distance feature dependencies but unfortunately deteriorate local feature details. In this paper, we propose a hybrid network structure, termed Conformer, to take advantage of convolutional operations and self-attention mechanisms for enhanced representation learning. Conformer roots in the Feature Coupling Unit (FCU), which fuses local features and global representations under different resolutions in an interactive fashion. Conformer adopts a concurrent structure so that local features and global representations are retained to the maximum extent. Experiments show that Conformer, under the comparable parameter complexity, outperforms the visual transformer (DeiT-B) by 2.3% on ImageNet. On MSCOCO, it outperforms ResNet-101 by 3.7% and 3.6% mAPs for object detection and instance segmentation, respectively, demonstrating the great potential to be a general backbone network. Code is available at https://github.com/pengzhiliang/Conformer.