# Dual-stream Network for Visual Recognition

arXiv: https://arxiv.org/abs/2105.14734 · HTML: https://mlsanity.com/paper/2105.14734/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 62 references that are in the map.
- First posted on arXiv 31 May 2021.

## Builds on (most cited first, 30 of 48)

- [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)
- [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)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [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)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)

## Built on by (most cited first, 30 of 33)

- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [SPViT: Enabling Faster Vision Transformers via Soft Token Pruning](https://mlsanity.com/paper/2112.13890/) (2021)
- [Dual Aggregation Transformer for Image Super-Resolution](https://mlsanity.com/paper/2308.03364/) (2023)
- [CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention](https://mlsanity.com/paper/2209.14169/) (2022)
- [Can Language Understand Depth?](https://mlsanity.com/paper/2207.01077/) (2022)
- [PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection](https://mlsanity.com/paper/2303.08129/) (2023)
- [HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers](https://mlsanity.com/paper/2211.08110/) (2022)
- [MixFormer: Mixing Features across Windows and Dimensions](https://mlsanity.com/paper/2204.02557/) (2022)
- [Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention](https://mlsanity.com/paper/2112.14000/) (2021)
- [iQuery: Instruments as Queries for Audio-Visual Sound Separation](https://mlsanity.com/paper/2212.03814/) (2022)
- [ProTo: Program-Guided Transformer for Program-Guided Tasks](https://mlsanity.com/paper/2110.00804/) (2021)
- [Oriented Object Detection with Transformer](https://mlsanity.com/paper/2106.03146/) (2021)
- [DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion](https://mlsanity.com/paper/2111.10332/) (2021)
- [SATr: Slice Attention with Transformer for Universal Lesion Detection](https://mlsanity.com/paper/2203.07373/) (2022)
- [T-Mamba: A unified framework with Long-Range Dependency in dual-domain for 2D & 3D Tooth Segmentation](https://mlsanity.com/paper/2404.01065/) (2024)
- [TCCT: Tightly-Coupled Convolutional Transformer on Time Series Forecasting](https://mlsanity.com/paper/2108.12784/) (2021)
- [Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection](https://mlsanity.com/paper/2208.03062/) (2022)
- [Learning Visual Abstract Reasoning through Dual-Stream Networks](https://mlsanity.com/paper/2411.19451/) (2024)
- [SP2T: Sparse Proxy Attention for Dual-stream Point Transformer](https://mlsanity.com/paper/2412.11540/) (2024)
- [TANet: A new Paradigm for Global Face Super-resolution via Transformer-CNN Aggregation Network](https://mlsanity.com/paper/2109.08174/) (2021)
- [Linear Array Network for Low-light Image Enhancement](https://mlsanity.com/paper/2201.08996/) (2022)
- [MAFormer: A Transformer Network with Multi-scale Attention Fusion for Visual Recognition](https://mlsanity.com/paper/2209.01620/) (2022)
- [Mutual Guidance and Residual Integration for Image Enhancement](https://mlsanity.com/paper/2211.13919/) (2022)
- [VITR: Augmenting Vision Transformers with Relation-Focused Learning for Cross-Modal Information Retrieval](https://mlsanity.com/paper/2302.06350/) (2023)
- [InterFormer: Interactive Local and Global Features Fusion for Automatic Speech Recognition](https://mlsanity.com/paper/2305.16342/) (2023)
- [UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval](https://mlsanity.com/paper/2508.04136/) (2025)

## Abstract (arXiv)

Transformers with remarkable global representation capacities achieve competitive results for visual tasks, but fail to consider high-level local pattern information in input images. In this paper, we present a generic Dual-stream Network (DS-Net) to fully explore the representation capacity of local and global pattern features for image classification. Our DS-Net can simultaneously calculate fine-grained and integrated features and efficiently fuse them. Specifically, we propose an Intra-scale Propagation module to process two different resolutions in each block and an Inter-Scale Alignment module to perform information interaction across features at dual scales. Besides, we also design a Dual-stream FPN (DS-FPN) to further enhance contextual information for downstream dense predictions. Without bells and whistles, the proposed DS-Net outperforms DeiT-Small by 2.4% in terms of top-1 accuracy on ImageNet-1k and achieves state-of-the-art performance over other Vision Transformers and ResNets. For object detection and instance segmentation, DS-Net-Small respectively outperforms ResNet-50 by 6.4% and 5.5% in terms of mAP on MSCOCO 2017, and surpasses the previous state-of-the-art scheme, which significantly demonstrates its potential to be a general backbone in vision tasks. The code will be released soon.