Data from: A large-scale benchmark for food image segmentation

Food image segmentation is a critical and indispensible task for developing health-related applications such as estimating food calories and nutrients. Existing food image segmentation models are underperforming due to two reasons: (1) there is a lack of high quality food image datasets with fine-grained ingredient labels and pixel-wise location masks---the existing datasets either carry coarse ingredient labels or are small in size; and (2) the complex appearance of food makes it difficult to localize and recognize ingredients in food images, e.g., the ingredients may overlap one another in the same image, and the identical ingredient may appear distinctly in different food images.In this work, 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 result in an average of 6 ingredient labels and pixel-wise masks per image. In addition, we propose a multi-modality pre-training approach called ReLeM that explicitly equips the model with rich and semantic food knowledge. In experiments, we use three popular semantic segmentation methods (i.e., Dilated Convolution based, Feature Pyramid based, and Vision Transformer based) as baselines, and evaluate them as well as ReLeM on our new datasets. We believe that the FoodSeg103 (and its extension FoodSeg154) and the pre-trained models using ReLeM can serve as a benchmark to facilitate future works in fine-grained food image understanding.

食品图像分割是开发卡路里估算、营养评估等健康相关应用的核心且不可或缺的任务。现有的食品图像分割模型性能欠佳，原因主要有二：其一，缺乏具备细粒度食材标签与逐像素位置掩码的高质量食品图像数据集——现有数据集要么仅提供粗粒度食材标签，要么样本体量偏小；其二，食品外观复杂多变，导致图像中食材的定位与识别难度陡增，例如同一张图像内的食材可能相互重叠，而同一类食材在不同食品图像中的表现形式也可能存在显著差异。本研究构建了全新的食品图像数据集FoodSeg103（及其扩展版本FoodSeg154），共包含9490张图像。我们为该数据集的所有图像标注了154个食材类别，平均每张图像对应6个食材标签及逐像素掩码。此外，本研究提出了一种名为ReLeM的多模态预训练方法，可显性地为模型注入丰富且具备语义属性的食品领域知识。实验阶段，我们选取三类主流语义分割方法作为基准模型，分别为基于膨胀卷积（Dilated Convolution）、特征金字塔（Feature Pyramid）以及视觉Transformer（Vision Transformer）的模型，并在自建数据集上对这些基准模型以及ReLeM方法进行了性能评估。我们认为，FoodSeg103（及其扩展版本FoodSeg154）以及基于ReLeM预训练得到的模型，可作为细粒度食品图像理解领域的基准数据集与基准方法，为后续相关研究提供支撑。