用轻量级Mamba模型提升低分辨率细粒度分类效果
Vision Mamba Distillation for Low-resolution Fine-grained Image Classification
- 用Mamba重构分类网络，提升特征提取能力
- 多层级知识蒸馏使模型准确率更高
- 参数少、计算量小，适合嵌入式设备
低分辨率细粒度图像分类近年进展显著，主要得益于超分辨率技术和知识蒸馏方法。然而这些方法导致模型参数和计算复杂度呈指数增长。为此，本文提出视觉Mamba蒸馏（ViMD）方法，以提升低分辨率细粒度分类的效率与效果。具体地，设计了一种轻量级超分辨率视觉Mamba分类网络（SRVM-Net），通过Mamba建模重构分类子网络，增强视觉特征提取能力；同时提出一种新型多层级Mamba知识蒸馏损失，将高分辨率视觉Mamba分类网络（HRVM-Net）作为教师模型的知识迁移至SRVM-Net学生模型。在七个公开细粒度分类数据集上的大量实验表明，ViMD达到新最佳性能。相比同类方法，其在更高准确率下参数更少、浮点运算量更低，更适合嵌入式设备应用。代码已开源。
原文摘要 · Abstract (English)
Low-resolution fine-grained image classification has recently made significant progress, largely thanks to the super-resolution techniques and knowledge distillation methods. However, these approaches lead to an exponential increase in the number of parameters and computational complexity of models. In order to solve this problem, in this letter, we propose a Vision Mamba Distillation (ViMD) approach to enhance the effectiveness and efficiency of low-resolution fine-grained image classification. Concretely, a lightweight super-resolution vision Mamba classification network (SRVM-Net) is proposed to improve its capability for extracting visual features by redesigning the classification sub-network with Mamba modeling. Moreover, we design a novel multi-level Mamba knowledge distillation loss boosting the performance, which can transfer prior knowledge obtained from a High-resolution Vision Mamba classification Network (HRVM-Net) as a teacher into the proposed SRVM-Net as a student. Extensive experiments on seven public fine-grained classification datasets related to benchmarks confirm our ViMD achieves a new state-of-the-art performance. While having higher accuracy, ViMD outperforms similar methods with fewer parameters and FLOPs, which is more suitable for embedded device applications. Code is available at https://github.com/boa2004plaust/ViMD.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。