# Mamba-R: Vision Mamba ALSO Needs Registers

arXiv: https://arxiv.org/abs/2405.14858 · HTML: https://mlsanity.com/paper/2405.14858/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 41 of its 54 references that are in the map.
- First posted on arXiv 23 May 2024.

## Placed in

- State-space sequence models (S4, Mamba) / [Vision Mamba backbones](https://mlsanity.com/ssm/vision-mamba-backbones/)

## Builds on (most cited first, 30 of 41)

- [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)
- [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)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [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)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [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)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [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)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023)
- [Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers](https://mlsanity.com/paper/2110.13985/) (2021)
- [HiPPO: Recurrent Memory with Optimal Polynomial Projections](https://mlsanity.com/paper/2008.07669/) (2020)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)

## Built on by (most cited first, 30 of 41)

- [Vision-LSTM: xLSTM as Generic Vision Backbone](https://mlsanity.com/paper/2406.04303/) (2024)
- [A Survey of Mamba](https://mlsanity.com/paper/2408.01129/) (2024)
- [Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More](https://mlsanity.com/paper/2502.03738/) (2025)
- [Autoregressive Pretraining with Mamba in Vision](https://mlsanity.com/paper/2406.07537/) (2024)
- [Mamba in Vision: A Comprehensive Survey of Techniques and Applications](https://mlsanity.com/paper/2410.03105/) (2024)
- [Vision Transformers Need More Than Registers](https://mlsanity.com/paper/2602.22394/) (2026)
- [MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining](https://mlsanity.com/paper/2410.00871/) (2024)
- [M4V: Multimodal Mamba for Efficient Text-to-Video Generation](https://mlsanity.com/paper/2506.10915/) (2025)
- [On the Optimal Memorization Capacity of Transformers](https://mlsanity.com/paper/2409.17677/) (2024)
- [LoG-VMamba: Local-Global Vision Mamba for Medical Image Segmentation](https://mlsanity.com/paper/2408.14415/) (2024)
- [Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency](https://mlsanity.com/paper/2410.07599/) (2024)
- [A Survey on Mamba Architecture for Vision Applications](https://mlsanity.com/paper/2502.07161/) (2025)
- [Vision Mamba in Remote Sensing: A Comprehensive Survey of Techniques, Applications and Outlook](https://mlsanity.com/paper/2505.00630/) (2025)
- [ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models](https://mlsanity.com/paper/2504.00037/) (2025)
- [SF-Mamba: Rethinking State Space Model for Vision](https://mlsanity.com/paper/2603.16423/) (2026)
- [Leveraging Registers in Vision Transformers for Robust Adaptation](https://mlsanity.com/paper/2501.04784/) (2025)
- [UD-Mamba: A pixel-level uncertainty-driven Mamba model for medical image segmentation](https://mlsanity.com/paper/2502.02024/) (2025)
- [VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretraining](https://mlsanity.com/paper/2503.12332/) (2025)
- [Imagine Before Concentration: Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval](https://mlsanity.com/paper/2604.03653/) (2026)
- [HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet](https://mlsanity.com/paper/2604.14724/) (2026)
- [MambaNUT: Nighttime UAV Tracking via Mamba-based Adaptive Curriculum Learning](https://mlsanity.com/paper/2412.00626/) (2024)
- [MrTrack: Register Mamba for Needle Tracking with Rapid Reciprocating Motion during Ultrasound-Guided Aspiration Biopsy](https://mlsanity.com/paper/2505.09450/) (2025)
- [Enhancing Transformer-Based Vision Models: Addressing Feature Map Anomalies Through Novel Optimization Strategies](https://mlsanity.com/paper/2509.19687/) (2025)
- [A Decomposition-based State Space Model for Multivariate Time-Series Forecasting](https://mlsanity.com/paper/2602.05389/) (2026)
- [FractalMamba++: Scaling Vision Mamba Across Resolutions via Hilbert Fractal Geometry](https://mlsanity.com/paper/2505.14062/) (2025)
- [LBMamba: Locally Bi-directional Mamba](https://mlsanity.com/paper/2506.15976/) (2025)
- [RNN as Linear Transformer: A Closer Investigation into Representational Potentials of Visual Mamba Models](https://mlsanity.com/paper/2511.18380/) (2025)
- [SVD-ViT: Does SVD Make Vision Transformers Attend More to the Foreground?](https://mlsanity.com/paper/2602.02765/) (2026)
- [Partial Ring Scan: Revisiting Scan Order in Vision State Space Models](https://mlsanity.com/paper/2602.04170/) (2026)
- [Vision SmolMamba: Spike-Guided Token Pruning for Energy-Efficient Spiking State-Space Vision Models](https://mlsanity.com/paper/2604.25570/) (2026)

## Abstract (arXiv)

Similar to Vision Transformers, this paper identifies artifacts also present within the feature maps of Vision Mamba. These artifacts, corresponding to high-norm tokens emerging in low-information background areas of images, appear much more severe in Vision Mamba -- they exist prevalently even with the tiny-sized model and activate extensively across background regions. To mitigate this issue, we follow the prior solution of introducing register tokens into Vision Mamba. To better cope with Mamba blocks' uni-directional inference paradigm, two key modifications are introduced: 1) evenly inserting registers throughout the input token sequence, and 2) recycling registers for final decision predictions. We term this new architecture Mamba-R. Qualitative observations suggest, compared to vanilla Vision Mamba, Mamba-R's feature maps appear cleaner and more focused on semantically meaningful regions. Quantitatively, Mamba-R attains stronger performance and scales better. For example, on the ImageNet benchmark, our base-size Mamba-R attains 83.0% accuracy, significantly outperforming Vim-B's 81.8%; furthermore, we provide the first successful scaling to the large model size (i.e., with 341M parameters), attaining a competitive accuracy of 83.6% (84.5% if finetuned with 384x384 inputs). Additional validation on the downstream semantic segmentation task also supports Mamba-R's efficacy. Code is available at https://github.com/wangf3014/Mamba-Reg.