# RMT: Retentive Networks Meet Vision Transformers

arXiv: https://arxiv.org/abs/2309.11523 · HTML: https://mlsanity.com/paper/2309.11523/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- Builds on 76 of its 86 references that are in the map.
- First posted on arXiv 20 Sep 2023.

## Builds on (most cited first, 30 of 76)

- [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)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [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)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (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)
- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023)

## Built on by (most cited first, 30 of 68)

- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures](https://mlsanity.com/paper/2403.02308/) (2024)
- [The Hidden Attention of Mamba Models](https://mlsanity.com/paper/2403.01590/) (2024)
- [DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation](https://mlsanity.com/paper/2410.18666/) (2024)
- [Breaking the Low-Rank Dilemma of Linear Attention](https://mlsanity.com/paper/2411.07635/) (2024)
- [DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation](https://mlsanity.com/paper/2504.04701/) (2025)
- [VSSD: Vision Mamba with Non-Causal State Space Duality](https://mlsanity.com/paper/2407.18559/) (2024)
- [ViT3: Unlocking Test-Time Training in Vision](https://mlsanity.com/paper/2512.01643/) (2025)
- [Rectifying Magnitude Neglect in Linear Attention](https://mlsanity.com/paper/2507.00698/) (2025)
- [Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation](https://mlsanity.com/paper/2405.16504/) (2024)
- [Do we really have to filter out random noise in pre-training data for language models?](https://mlsanity.com/paper/2502.06604/) (2025)
- [Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures](https://mlsanity.com/paper/2503.16067/) (2025)
- [SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention](https://mlsanity.com/paper/2407.05128/) (2024)
- [Hadamard product in deep learning: Introduction, Advances and Challenges](https://mlsanity.com/paper/2504.13112/) (2025)
- [Vision Transformer with Sparse Scan Prior](https://mlsanity.com/paper/2405.13335/) (2024)
- [Large Language Models Meet Computer Vision: A Brief Survey](https://mlsanity.com/paper/2311.16673/) (2023)
- [SVIPTR: Fast and Efficient Scene Text Recognition with Vision Permutable Extractor](https://mlsanity.com/paper/2401.10110/) (2024)
- [Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens](https://mlsanity.com/paper/2405.13337/) (2024)
- [AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation](https://mlsanity.com/paper/2411.04967/) (2024)
- [RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization](https://mlsanity.com/paper/2406.16004/) (2024)
- [Depth Matters: Exploring Deep Interactions of RGB-D for Semantic Segmentation in Traffic Scenes](https://mlsanity.com/paper/2409.07995/) (2024)
- [AnchorFormer: Differentiable Anchor Attention for Efficient Vision Transformer](https://mlsanity.com/paper/2505.16463/) (2025)
- [S2AFormer: Strip Self-Attention for Efficient Vision Transformer](https://mlsanity.com/paper/2505.22195/) (2025)
- [SAGA: Selective Adaptive Gating for Efficient and Expressive Linear Attention](https://mlsanity.com/paper/2509.12817/) (2025)
- [A Manifold Representation of the Key in Vision Transformers](https://mlsanity.com/paper/2402.00534/) (2024)
- [DuoFormer: Leveraging Hierarchical Visual Representations by Local and Global Attention](https://mlsanity.com/paper/2407.13920/) (2024)
- [HAD: Hybrid Architecture Distillation Outperforms Teacher in Genomic Sequence Modeling](https://mlsanity.com/paper/2505.20836/) (2025)
- [Norm×Direction: Restoring the Missing Query Norm in Vision Linear Attention](https://mlsanity.com/paper/2506.21137/) (2025)
- [RetSeg: Retention-based Colorectal Polyps Segmentation Network](https://mlsanity.com/paper/2310.05446/) (2023)
- [HybridHash: Hybrid Convolutional and Self-Attention Deep Hashing for Image Retrieval](https://mlsanity.com/paper/2405.07524/) (2024)

## Abstract (arXiv)

Vision Transformer (ViT) has gained increasing attention in the computer vision community in recent years. However, the core component of ViT, Self-Attention, lacks explicit spatial priors and bears a quadratic computational complexity, thereby constraining the applicability of ViT. To alleviate these issues, we draw inspiration from the recent Retentive Network (RetNet) in the field of NLP, and propose RMT, a strong vision backbone with explicit spatial prior for general purposes. Specifically, we extend the RetNet's temporal decay mechanism to the spatial domain, and propose a spatial decay matrix based on the Manhattan distance to introduce the explicit spatial prior to Self-Attention. Additionally, an attention decomposition form that adeptly adapts to explicit spatial prior is proposed, aiming to reduce the computational burden of modeling global information without disrupting the spatial decay matrix. Based on the spatial decay matrix and the attention decomposition form, we can flexibly integrate explicit spatial prior into the vision backbone with linear complexity. Extensive experiments demonstrate that RMT exhibits exceptional performance across various vision tasks. Specifically, without extra training data, RMT achieves **84.8%** and **86.1%** top-1 acc on ImageNet-1k with **27M/4.5GFLOPs** and **96M/18.2GFLOPs**. For downstream tasks, RMT achieves **54.5** box AP and **47.2** mask AP on the COCO detection task, and **52.8** mIoU on the ADE20K semantic segmentation task. Code is available at https://github.com/qhfan/RMT