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

• URL: http://arxiv.org/abs/2509.19028v2
• Date: Wed, 22 Oct 2025 06:53:52 GMT
• Title: Weakly Supervised Food Image Segmentation using Vision Transformers and Segment Anything Model
• Authors: Ioannis Sarafis, Alexandros Papadopoulos, Anastasios Delopoulos,
• Abstract summary: We propose a weakly supervised semantic segmentation approach for food images.<n>We use the Segment Anything Model (SAM) along with the attention mechanisms of Vision Transformers (ViTs)<n>We envision the proposed approach as a tool to accelerate food image annotation tasks or as an integrated component in food and nutrition tracking applications.
• Score: 45.641643140398735
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 attention mechanisms of Vision Transformers (ViTs). Specifically, we use class activation maps (CAMs) from ViTs to generate prompts for SAM, resulting in masks suitable for food image segmentation. The ViT model, a Swin Transformer, is trained exclusively using image-level annotations, eliminating the need for pixel-level annotations during training. Additionally, to enhance the quality of the SAM-generated masks, we examine the use of image preprocessing techniques in combination with single-mask and multi-mask SAM generation strategies. The methodology is evaluated on the FoodSeg103 dataset, generating an average of 2.4 masks per image (excluding background), and achieving an mIoU of 0.54 for the multi-mask scenario. We envision the proposed approach as a tool to accelerate food image annotation tasks or as an integrated component in food and nutrition tracking applications.

Related papers

• SAMTok: Representing Any Mask with Two Words [70.74140779649856]
  We present SAMTok, a discrete mask tokenizer that converts any region mask into two special tokens.<n>By treating masks as new language tokens, SAMTok enables base MLLMs to learn pixel-wise capabilities.<n>QwenVL-SAMTok attains state-of-the-art or comparable results on region captioning, region VQA, grounded conversation, referring segmentation, scene graph parsing, and multi-round interactive segmentation.
  arXiv  Detail & Related papers  (2026-01-22T16:44:09Z)
• Evaluating SAM2 for Video Semantic Segmentation [60.157605818225186]
  The Anything Model 2 (SAM2) has proven to be a powerful foundation model for promptable visual object segmentation in both images and videos.<n>This paper explores the extension of SAM2 to dense Video Semantic (VSS)<n>Our experiments suggest that leveraging SAM2 enhances overall performance in VSS, primarily due to its precise predictions of object boundaries.
  arXiv  Detail & Related papers  (2025-12-01T15:15:16Z)
• LlamaSeg: Image Segmentation via Autoregressive Mask Generation [46.17509085054758]
  We present LlamaSeg, a visual autoregressive framework that unifies multiple image segmentation tasks via natural language instructions.<n>We reformulate image segmentation as a visual generation problem, representing masks as "visual" tokens and employing a LLaMA-style Transformer to predict them directly from image inputs.
  arXiv  Detail & Related papers  (2025-05-26T02:22:41Z)
• PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentation [19.65118388712439]
  We introduce a novel prompt-driven adapter into SAM, namely Prompt Adapter Segment Anything Model (PA-SAM) By exclusively training the prompt adapter, PA-SAM extracts detailed information from images and optimize the mask decoder feature at both sparse and dense prompt levels. Experimental results demonstrate that our PA-SAM outperforms other SAM-based methods in high-quality, zero-shot, and open-set segmentation.
  arXiv  Detail & Related papers  (2024-01-23T19:20:22Z)
• FoodSAM: Any Food Segmentation [10.467966270491228]
  We propose a novel framework, called FoodSAM, to address the lack of class-specific information in SAM-generated masks. FoodSAM integrates the coarse semantic mask with SAM-generated masks to enhance semantic segmentation quality. FoodSAM stands as the first-ever work to achieve instance, panoptic, and promptable segmentation on food images.
  arXiv  Detail & Related papers  (2023-08-11T04:42:10Z)
• Transferring Knowledge for Food Image Segmentation using Transformers and Convolutions [65.50975507723827]
  Food image segmentation is an important task that has ubiquitous applications, such as estimating the nutritional value of a plate of food. One challenge is that food items can overlap and mix, making them difficult to distinguish. Two models are trained and compared, one based on convolutional neural networks and the other on Bidirectional representation for Image Transformers (BEiT) The BEiT model outperforms the previous state-of-the-art model by achieving a mean intersection over union of 49.4 on FoodSeg103.
  arXiv  Detail & Related papers  (2023-06-15T15:38:10Z)
• MaskSketch: Unpaired Structure-guided Masked Image Generation [56.88038469743742]
  MaskSketch is an image generation method that allows spatial conditioning of the generation result using a guiding sketch as an extra conditioning signal during sampling. We show that intermediate self-attention maps of a masked generative transformer encode important structural information of the input image. Our results show that MaskSketch achieves high image realism and fidelity to the guiding structure.
  arXiv  Detail & Related papers  (2023-02-10T20:27:02Z)
• GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation [16.900404701997502]
  We propose a GAN-based approach that generates images conditioned on latent masks. We show that such mask-conditioned image generation can be learned faithfully when conditioning the masks in a hierarchical manner. It also lets us generate image-mask pairs for training a segmentation network, which outperforms the state-of-the-art unsupervised segmentation methods on established benchmarks.
  arXiv  Detail & Related papers  (2021-12-02T07:57:56Z)
• Segmenter: Transformer for Semantic Segmentation [79.9887988699159]
  We introduce Segmenter, a transformer model for semantic segmentation. We build on the recent Vision Transformer (ViT) and extend it to semantic segmentation. It outperforms the state of the art on the challenging ADE20K dataset and performs on-par on Pascal Context and Cityscapes.
  arXiv  Detail & Related papers  (2021-05-12T13:01:44Z)
• A Large-Scale Benchmark for Food Image Segmentation [62.28029856051079]
  We build a new food image dataset FoodSeg103 (and its extension FoodSeg154) containing 9,490 images. We annotate these images with 154 ingredient classes and each image has an average of 6 ingredient labels and pixel-wise masks. We propose a multi-modality pre-training approach called ReLeM that explicitly equips a segmentation model with rich and semantic food knowledge.
  arXiv  Detail & Related papers  (2021-05-12T03:00:07Z)

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.