arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.09046cs.CVeess.IV
收藏

食物图像的自监督视觉表示学习

Self-Supervised Visual Representation Learning on Food Images

Purdue University(普渡大学)

Andrew Peng, Jiangpeng He, Fengqing Zhu

摘要:

食物图像分析是基于图像的饮食评估的基础,基于图像的饮食评估是使用捕获的食物或饮食场景图像来监测食物种类和消耗多少能量的过程。现有的基于深度学习的方法基于每个食物图像的人类注释来学习下游任务的视觉表示。然而,现实生活中的大多数食物图像是在没有标签的情况下获得的,并且数据注释需要大量的时间和人力,这对于现实世界的应用是不可行的。为了利用大量的未标记图像,许多现有的工作集中在无监督或自监督学习的视觉表示直接从未标记的数据。然而,这些现有的工作都没有专注于食物图像,这是更具有挑战性的比一般的对象,由于其高的类间相似性和类内方差。在本文中,我们专注于现有的代表性的自监督学习方法在食品图像上的实现和分析。具体来说,我们首先在Food-101数据集上比较了六种选定的自监督学习模型的性能。然后,我们分析每个选定模型在食物数据上训练时的优缺点,以确定有助于提高性能的关键因素。最后,我们提出了几个想法,为未来的工作自我监督视觉表示学习的食物图像。

英文摘要:

Food image analysis is the groundwork for image-based dietary assessment, which is the process of monitoring what kinds of food and how much energy is consumed using captured food or eating scene images. Existing deep learning-based methods learn the visual representation for downstream tasks based on human annotation of each food image. However, most food images in real life are obtained without labels, and data annotation requires plenty of time and human effort, which is not feasible for real-world applications. To make use of the vast amount of unlabeled images, many existing works focus on unsupervised or self-supervised learning of visual representations directly from unlabeled data. However, none of these existing works focus on food images, which is more challenging than general objects due to its high inter-class similarity and intra-class variance. In this paper, we focus on the implementation and analysis of existing representative self-supervised learning methods on food images. Specifically, we first compare the performance of six selected self-supervised learning models on the Food-101 dataset. Then we analyze the pros and cons of each selected model when training on food data to identify the key factors that can help improve the performance. Finally, we propose several ideas for future work on self-supervised visual representation learning for food images.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑