# MambaLiteSR: Image Super-Resolution with Low-Rank Mamba using Knowledge Distillation

arXiv: https://arxiv.org/abs/2502.14090 · HTML: https://mlsanity.com/paper/2502.14090/

## Key facts

- Cited by 3 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 21 of its 64 references that are in the map.
- First posted on arXiv 19 Feb 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Vision Mamba backbones](https://mlsanity.com/ssm/vision-mamba-backbones/)
- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Learning Deep CNN Denoiser Prior for Image Restoration](https://mlsanity.com/paper/1704.03264/) (2017)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [MambaVision: A Hybrid Mamba-Transformer Vision Backbone](https://mlsanity.com/paper/2407.08083/) (2024)
- [Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration](https://mlsanity.com/paper/1508.02848/) (2015)
- [Generative AI](https://mlsanity.com/paper/2309.07930/) (2023)
- [Residual Local Feature Network for Efficient Super-Resolution](https://mlsanity.com/paper/2205.07514/) (2022)
- [DVMSR: Distillated Vision Mamba for Efficient Super-Resolution](https://mlsanity.com/paper/2405.03008/) (2024)
- [Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution](https://mlsanity.com/paper/2410.10140/) (2024)
- [edge-SR: Super-Resolution For The Masses](https://mlsanity.com/paper/2108.10335/) (2021)
- [Squeezed Edge YOLO: Onboard Object Detection on Edge Devices](https://mlsanity.com/paper/2312.11716/) (2023)
- [ReProHRL: Towards Multi-Goal Navigation in the Real World using Hierarchical Agents](https://mlsanity.com/paper/2308.08737/) (2023)
- [TinyM2Net-V3: Memory-Aware Compressed Multimodal Deep Neural Networks for Sustainable Edge Deployment](https://mlsanity.com/paper/2405.12353/) (2024)
- [Decentralised Resource Sharing in TinyML: Wireless Bilayer Gossip Parallel SGD for Collaborative Learning](https://mlsanity.com/paper/2501.04817/) (2025)

## Built on by (most cited first, 3 of 3)

- [MedMambaLite: Hardware-Aware Mamba for Medical Image Classification](https://mlsanity.com/paper/2508.05049/) (2025)
- [EdgeNavMamba: Mamba Optimized Object Detection for Energy Efficient Edge Devices](https://mlsanity.com/paper/2510.14946/) (2025)
- [Context-Driven Performance Modeling for Causal Inference Operators on Neural Processing Units](https://mlsanity.com/paper/2509.25155/) (2025)

## Abstract (arXiv)

Generative Artificial Intelligence (AI) has gained significant attention in recent years, revolutionizing various applications across industries. Among these, advanced vision models for image super-resolution are in high demand, particularly for deployment on edge devices where real-time processing is crucial. However, deploying such models on edge devices is challenging due to limited computing power and memory. In this paper, we present MambaLiteSR, a novel lightweight image Super-Resolution (SR) model that utilizes the architecture of Vision Mamba. It integrates State Space Blocks and a reconstruction module for efficient feature extraction. To optimize efficiency without affecting performance, MambaLiteSR employs knowledge distillation to transfer key insights from a larger Mamba-based teacher model to a smaller student model via hyperparameter tuning. Through mathematical analysis of model parameters and their impact on PSNR, we identify key factors and adjust them accordingly. Our comprehensive evaluation shows that MambaLiteSR outperforms state-of-the-art edge SR methods by reducing power consumption while maintaining competitive PSNR and SSIM scores across benchmark datasets. It also reduces power usage during training via low-rank approximation. Moreover, MambaLiteSR reduces parameters with minimal performance loss, enabling efficient deployment of generative AI models on resource-constrained devices. Deployment on the embedded NVIDIA Jetson Orin Nano confirms the superior balance of MambaLiteSR size, latency, and efficiency. Experiments show that MambaLiteSR achieves performance comparable to both the baseline and other edge models while using 15% fewer parameters. It also improves power consumption by up to 58% compared to state-of-the-art SR edge models, all while maintaining low energy use during training.