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

• URL: http://arxiv.org/abs/2507.17347v3
• Date: Mon, 28 Jul 2025 08:44:20 GMT
• Title: Swin-TUNA : A Novel PEFT Approach for Accurate Food Image Segmentation
• Authors: Haotian Chen, Zhiyong Xiao,
• Abstract summary: This paper introduces TUNable Adapter module (Swin-TUNA), a.<n> Efficient Fine-Tuning (PEFT) method that integrates multiscale trainable adapters into the.<n>Swin Transformer architecture.<n> Experiments demonstrate that this method achieves mIoU of 50.56% and 74.94% on the FoodSeg103 and UECFoodPix Complete datasets.
• Score: 3.061662434597098
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• MuSASplat: Efficient Sparse-View 3D Gaussian Splats via Lightweight Multi-Scale Adaptation [92.57609195819647]
  MuSASplat is a novel framework that dramatically reduces the computational burden of training pose-free feed-forward 3D Gaussian splats models.<n>Central to our approach is a lightweight Multi-Scale Adapter that enables efficient fine-tuning of ViT-based architectures with only a small fraction of training parameters.
  arXiv  Detail & Related papers  (2025-12-08T04:56:46Z)
• Lightweight Vision Transformer with Window and Spatial Attention for Food Image Classification [1.1472801896854488]
  We propose a lightweight food image classification algorithm that integrates a Window Multi-Head Attention Mechanism (WMHAM) and a Spatial Attention Mechanism (SAM)<n>Our model achieves accuracies of 95.24% and 94.33%, respectively, while significantly reducing parameters and FLOPs compared with baseline methods.
  arXiv  Detail & Related papers  (2025-09-23T06:23:50Z)
• Optimizing Specific and Shared Parameters for Efficient Parameter Tuning [46.57365875007367]
  We propose SaS, a novel PETL method that effectively mitigates distributional shifts during fine-tuning.<n>SaS captures common statistical characteristics across layers using low-rank projections.<n>Experiments on diverse downstream tasks, few-shot settings and domain generalization demonstrate that SaS significantly enhances performance.
  arXiv  Detail & Related papers  (2025-04-04T13:43:54Z)
• Hyper Compressed Fine-Tuning of Large Foundation Models with Quantum Inspired Adapters [0.0]
  emphQuantum-Inspired Adapters, a PEFT approach inspired by Hamming-weight quantum circuits from quantum machine learning literature.<n>We test our proposed adapters by adapting large language models and large vision transformers on benchmark datasets.
  arXiv  Detail & Related papers  (2025-02-10T13:06:56Z)
• RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks [16.512587987753967]
  RECAST is a novel method that dramatically reduces task-specific trainable parameters to fewer than 50.<n>We show that RECAST outperforms the state-of-the-art by up to 3% across various scales, architectures, and parameter spaces.
  arXiv  Detail & Related papers  (2024-11-25T19:08:38Z)
• TOAST: Transformer Optimization using Adaptive and Simple Transformations [40.311292704886235]
  We introduce TOAST, a framework that exploits redundancies to approximate entire transformer blocks with lightweight closed-form mappings.<n>Results show that large portions of transformer depth can be replaced by trivial functions, opening a new perspective on efficient foundation models.
  arXiv  Detail & Related papers  (2024-10-07T11:35:24Z)
• RoDE: Linear Rectified Mixture of Diverse Experts for Food Large Multi-Modal Models [96.43285670458803]
  Uni-Food is a unified food dataset that comprises over 100,000 images with various food labels.<n>Uni-Food is designed to provide a more holistic approach to food data analysis.<n>We introduce a novel Linear Rectification Mixture of Diverse Experts (RoDE) approach to address the inherent challenges of food-related multitasking.
  arXiv  Detail & Related papers  (2024-07-17T16:49:34Z)
• ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections [59.839926875976225]
  We propose the ETHER transformation family, which performs Efficient fineTuning via HypErplane Reflections. In particular, we introduce ETHER and its relaxation ETHER+, which match or outperform existing PEFT methods with significantly fewer parameters.
  arXiv  Detail & Related papers  (2024-05-30T17:26:02Z)
• Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation [67.13876021157887]
  Dynamic Tuning (DyT) is a novel approach to improve both parameter and inference efficiency for ViT adaptation. DyT achieves superior performance compared to existing PEFT methods while evoking only 71% of their FLOPs on the VTAB-1K benchmark.
  arXiv  Detail & Related papers  (2024-03-18T14:05:52Z)
• Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts [52.39959535724677]
  We introduce an alternative solution to improve the generalization of image restoration models. We propose AdaptIR, a Mixture-of-Experts (MoE) with multi-branch design to capture local, global, and channel representation bases. Our AdaptIR achieves stable performance on single-degradation tasks, and excels in hybrid-degradation tasks, with fine-tuning only 0.6% parameters for 8 hours.
  arXiv  Detail & Related papers  (2023-12-12T14:27:59Z)
• Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model [81.55141188169621]
  We equip PEFT with a cross-block orchestration mechanism to enable the adaptation of the Segment Anything Model (SAM) to various downstream scenarios. We propose an intra-block enhancement module, which introduces a linear projection head whose weights are generated from a hyper-complex layer. Our proposed approach consistently improves the segmentation performance significantly on novel scenarios with only around 1K additional parameters.
  arXiv  Detail & Related papers  (2023-11-28T11:23:34Z)
• ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization [100.90624220423634]
  We present ComPEFT, a novel method for compressing fine-tuning residuals (task vectors) of PEFT based models. In extensive evaluation across T5, T0, and LLaMA-based models with 200M - 65B parameters, ComPEFT achieves compression ratios of 8x - 50x.
  arXiv  Detail & Related papers  (2023-11-22T05:28:59Z)
• Hierarchical Side-Tuning for Vision Transformers [33.536948382414316]
  Fine-tuning pre-trained Vision Transformers (ViTs) has showcased significant promise in enhancing visual recognition tasks. PETL has shown potential for achieving high performance with fewer parameter updates compared to full fine-tuning. This paper introduces Hierarchical Side-Tuning (HST), an innovative PETL method facilitating the transfer of ViT models to diverse downstream tasks.
  arXiv  Detail & Related papers  (2023-10-09T04:16:35Z)
• EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm [111.17100512647619]
  This paper explains the rationality of Vision Transformer by analogy with the proven practical evolutionary algorithm (EA) We propose a novel pyramid EATFormer backbone that only contains the proposed EA-based transformer (EAT) block. Massive quantitative and quantitative experiments on image classification, downstream tasks, and explanatory experiments demonstrate the effectiveness and superiority of our approach.
  arXiv  Detail & Related papers  (2022-06-19T04:49:35Z)

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.