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

• URL: http://arxiv.org/abs/2502.14090v1
• Date: Wed, 19 Feb 2025 20:32:03 GMT
• Title: MambaLiteSR: Image Super-Resolution with Low-Rank Mamba using Knowledge Distillation
• Authors: Romina Aalishah, Mozhgan Navardi, Tinoosh Mohsenin,
• Abstract summary: MambaLiteSR is a novel lightweight image Super-Resolution (SR) model that utilizes the architecture of Vision Mamba. We 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.
• Score: 0.5243460995467893
• License:
• Abstract: 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.

Related papers

• Low Resource Video Super-resolution using Memory and Residual Deformable Convolutions [3.018928786249079]
  Transformer-based video super-resolution (VSR) models have set new benchmarks in recent years, but their substantial computational demands make most of them unsuitable for deployment on resource-constrained devices. We propose a novel lightweight, parameter-efficient deep residual deformable convolution network for VSR. With just 2.3 million parameters, our model achieves state-of-the-art SSIM of 0.9175 on the REDS4 dataset.
  arXiv  Detail & Related papers  (2025-02-03T20:46:15Z)
• Vision Mamba Distillation for Low-resolution Fine-grained Image Classification [11.636461046632183]
  We propose a Vision Mamba Distillation (ViMD) approach to enhance the effectiveness and efficiency of low-resolution fine-grained image classification. ViMD outperforms similar methods with fewer parameters and FLOPs, which is more suitable for embedded device applications.
  arXiv  Detail & Related papers  (2024-11-27T01:29:44Z)
• MobileMamba: Lightweight Multi-Receptive Visual Mamba Network [51.33486891724516]
  Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs. We propose the MobileMamba framework, which balances efficiency and performance. MobileMamba achieves up to 83.6% on Top-1, surpassing existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-11-24T18:01:05Z)
• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• Cross-Scan Mamba with Masked Training for Robust Spectral Imaging [51.557804095896174]
  We propose the Cross-Scanning Mamba, named CS-Mamba, that employs a Spatial-Spectral SSM for global-local balanced context encoding. Experiment results show that our CS-Mamba achieves state-of-the-art performance and the masked training method can better reconstruct smooth features to improve the visual quality.
  arXiv  Detail & Related papers  (2024-08-01T15:14:10Z)
• Benchmarking Deep Learning Models on NVIDIA Jetson Nano for Real-Time Systems: An Empirical Investigation [2.3636539018632616]
  This work empirically investigates the optimization of complex deep learning models to analyze their functionality on an embedded device. It evaluates the effectiveness of the optimized models in terms of their inference speed for image classification and video action detection.
  arXiv  Detail & Related papers  (2024-06-25T17:34:52Z)
• Frequency-Assisted Mamba for Remote Sensing Image Super-Resolution [49.902047563260496]
  We develop the first attempt to integrate the Vision State Space Model (Mamba) for remote sensing image (RSI) super-resolution. To achieve better SR reconstruction, building upon Mamba, we devise a Frequency-assisted Mamba framework, dubbed FMSR. Our FMSR features a multi-level fusion architecture equipped with the Frequency Selection Module (FSM), Vision State Space Module (VSSM), and Hybrid Gate Module (HGM)
  arXiv  Detail & Related papers  (2024-05-08T11:09:24Z)
• DVMSR: Distillated Vision Mamba for Efficient Super-Resolution [7.551130027327461]
  We propose DVMSR, a novel lightweight Image SR network that incorporates Vision Mamba and a distillation strategy. Our proposed DVMSR can outperform state-of-the-art efficient SR methods in terms of model parameters.
  arXiv  Detail & Related papers  (2024-05-05T17:34:38Z)
• TSCM: A Teacher-Student Model for Vision Place Recognition Using Cross-Metric Knowledge Distillation [6.856317526681759]
  Visual place recognition plays a pivotal role in autonomous exploration and navigation of mobile robots. Existing methods overcome this by exploiting powerful yet large networks. We propose a high-performance teacher and lightweight student distillation framework called TSCM.
  arXiv  Detail & Related papers  (2024-04-02T02:29:41Z)
• A-SDM: Accelerating Stable Diffusion through Redundancy Removal and Performance Optimization [54.113083217869516]
  In this work, we first explore the computational redundancy part of the network. We then prune the redundancy blocks of the model and maintain the network performance. Thirdly, we propose a global-regional interactive (GRI) attention to speed up the computationally intensive attention part.
  arXiv  Detail & Related papers  (2023-12-24T15:37:47Z)
• Powerpropagation: A sparsity inducing weight reparameterisation [65.85142037667065]
  We introduce Powerpropagation, a new weight- parameterisation for neural networks that leads to inherently sparse models. Models trained in this manner exhibit similar performance, but have a distribution with markedly higher density at zero, allowing more parameters to be pruned safely. Here, we combine Powerpropagation with a traditional weight-pruning technique as well as recent state-of-the-art sparse-to-sparse algorithms, showing superior performance on the ImageNet benchmark.
  arXiv  Detail & Related papers  (2021-10-01T10:03:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.