Swin-TUNA : A Novel PEFT Approach for Accurate Food Image Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Haotian, Xiao, Zhiyong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918105219858432
author Chen, Haotian
Xiao, Zhiyong
author_facet Chen, Haotian
Xiao, Zhiyong
contents In the field of food image processing, efficient semantic segmentation techniques are crucial for industrial applications. However, existing large-scale Transformer-based models (such as FoodSAM) face challenges in meeting practical deploymentrequirements due to their massive parameter counts and high computational resource demands. This paper introduces TUNable Adapter module (Swin-TUNA), a Parameter Efficient Fine-Tuning (PEFT) method that integrates multiscale trainable adapters into the Swin Transformer architecture, achieving high-performance food image segmentation by updating only 4% of the parameters. The core innovation of Swin-TUNA lies in its hierarchical feature adaptation mechanism: it designs separable convolutions in depth and dimensional mappings of varying scales to address the differences in features between shallow and deep networks, combined with a dynamic balancing strategy for tasks-agnostic and task-specific features. Experiments demonstrate that this method achieves mIoU of 50.56% and 74.94% on the FoodSeg103 and UECFoodPix Complete datasets, respectively, surpassing the fully parameterized FoodSAM model while reducing the parameter count by 98.7% (to only 8.13M). Furthermore, Swin-TUNA exhibits faster convergence and stronger generalization capabilities in low-data scenarios, providing an efficient solution for assembling lightweight food image.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17347
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Swin-TUNA : A Novel PEFT Approach for Accurate Food Image Segmentation
Chen, Haotian
Xiao, Zhiyong
Computer Vision and Pattern Recognition
Artificial Intelligence
In the field of food image processing, efficient semantic segmentation techniques are crucial for industrial applications. However, existing large-scale Transformer-based models (such as FoodSAM) face challenges in meeting practical deploymentrequirements due to their massive parameter counts and high computational resource demands. This paper introduces TUNable Adapter module (Swin-TUNA), a Parameter Efficient Fine-Tuning (PEFT) method that integrates multiscale trainable adapters into the Swin Transformer architecture, achieving high-performance food image segmentation by updating only 4% of the parameters. The core innovation of Swin-TUNA lies in its hierarchical feature adaptation mechanism: it designs separable convolutions in depth and dimensional mappings of varying scales to address the differences in features between shallow and deep networks, combined with a dynamic balancing strategy for tasks-agnostic and task-specific features. Experiments demonstrate that this method achieves mIoU of 50.56% and 74.94% on the FoodSeg103 and UECFoodPix Complete datasets, respectively, surpassing the fully parameterized FoodSAM model while reducing the parameter count by 98.7% (to only 8.13M). Furthermore, Swin-TUNA exhibits faster convergence and stronger generalization capabilities in low-data scenarios, providing an efficient solution for assembling lightweight food image.
title Swin-TUNA : A Novel PEFT Approach for Accurate Food Image Segmentation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.17347