Vision Mamba Distillation for Low-resolution Fine-grained Image Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yao, Wang, Jiabao, Wang, Peichao, Zhang, Rui, Li, Yang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913587423870976
author Chen, Yao
Wang, Jiabao
Wang, Peichao
Zhang, Rui
Li, Yang
author_facet Chen, Yao
Wang, Jiabao
Wang, Peichao
Zhang, Rui
Li, Yang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17980
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Vision Mamba Distillation for Low-resolution Fine-grained Image Classification
Chen, Yao
Wang, Jiabao
Wang, Peichao
Zhang, Rui
Li, Yang
Computer Vision and Pattern Recognition
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.
title Vision Mamba Distillation for Low-resolution Fine-grained Image Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.17980