paper-with-me

홈 › Papers

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

2025-07-23 · Haotian Chen, Zhiyong Xiao arxiv

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.

📄 PDF Abstract BibTeX arXiv:2507.17347

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic SegmentationImage Segmentation

Results from the Paper

RankTaskDatasetModelMetrics
#1 Semantic Segmentation FoodSeg103 TUNable mIoU: 50.56

Similar Papers 제목 키워드 기반

Food Image Segmentation with LLM-Derived Ingredient Labels and Multimodal Fusion

2026-07-28 · Jui-Feng Chi, Wei-Ta Chu, Sheng-Long Lin arxiv

Food image segmentation plays a vital role in health-related applications such as nutrition tracking and personalized health monitoring. However, existing models often underperform on visually similar ingredients and rar…

Image Segmentation

An Empirical Study of Parameter Efficient Fine-tuning on Vision-Language Pre-train Model

2024-03-13 · Yuxin Tian, Mouxing Yang, Yunfan Li, Dayiheng Liu 외

Recent studies applied Parameter Efficient Fine-Tuning techniques (PEFTs) to efficiently narrow the performance gap between pre-training and downstream. There are two important factors for various PEFTs, namely, the acce…

parameter-efficient fine-tuning

Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement

2023-03-15 · ICCV 2023 1 · Fartash Faghri, Hadi Pouransari, Sachin Mehta, Mehrdad Farajtabar 외

We propose Dataset Reinforcement, a strategy to improve a dataset once such that the accuracy of any model architecture trained on the reinforced dataset is improved at no additional training cost for users. We propose a…

Data AugmentationKnowledge Distillationobject-detectionObject Detection

Weakly Supervised Food Image Segmentation using Vision Transformers and Segment Anything Model

2025-09-23 · Ioannis Sarafis, Alexandros Papadopoulos, Anastasios Delopoulos arxiv

In this paper, we propose a weakly supervised semantic segmentation approach for food images which takes advantage of the zero-shot capabilities and promptability of the Segment Anything Model (SAM) along with the attent…

Semantic SegmentationImage Segmentation

Empirical Study of PEFT techniques for Winter Wheat Segmentation

2023-10-03 · Mohamad Hasan Zahweh, Hasan Nasrallah, Mustafa Shukor, Ghaleb Faour 외

Parameter Efficient Fine Tuning (PEFT) techniques have recently experienced significant growth and have been extensively employed to adapt large vision and language models to various domains, enabling satisfactory model …

Out-of-Distribution Generalizationparameter-efficient fine-tuning