Towards Food Image Retrieval via Generalization-Oriented Sampling and Loss Function Design
文献类型：期刊论文
| 作者 | Song, Jiajun; Li, Zhuo; Min, Weiqing; Jiang, Shuqiang |
| 刊名 | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
 |
| 出版日期 | 2024 |
| 卷号 | 20期号:1页码:19 |
| ISSN号 | 1551-6857 |
| 关键词 | Food computing image retrieval deep learning |
| DOI | 10.1145/3600095 |
| 英文摘要 | Food computing has increasingly received widespread attention in the multimedia field. As a basic task of food computing, food image retrieval has wide applications, that is, food image retrieval can help users to find the desired food from a large number of food images. Besides, the retrieved information can be applied to establish a richer database for the subsequent food content-related recommendation. Food image retrieval aims to achieve better performance on novel categories. Thus, it is worth studying to transfer the embedding ability from the training set to the unseen test set, that is, the generalization of the model. Food is influenced by various factors, such as culture and geography, leading to great differences between domains, such as Asian food and western food. Therefore, it is challenging to study the generalization of the model in food image retrieval. In this article, we improve the classical metric learning framework and propose a generalization-oriented sampling strategy, which boosts the generalization of the model by maximizing the intra-class distance from a proportion of positive pairs to avoid the excessive distance compression in the embedding space. Considering that the existing optimization process is in an opposite direction to our proposed sampling strategy, we further propose an adaptive gradient assignment policy named gradient-adaptive optimization, which can alleviate the intra-class distance compression during optimization by assigning different gradients to different samples. Extensive evaluation on three popular food image datasets demonstrates the effectiveness of the proposed method. We also experiment on three popular general datasets to prove that solving the problem from the generalization can also improve the performance of general image retrieval. Code is available at https://github.com/Jiajun-ISIA/Generalization- oriented- Sampling- and- Loss. |
| 资助项目 | National Nature Science Foundation of China[61972378] ; National Nature Science Foundation of China[62125207] ; National Nature Science Foundation of China[U1936203] ; National Nature Science Foundation of China[U19B2040] ; CAAI-Huawei MindSpore Open Fund |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| 出版者 | ASSOC COMPUTING MACHINERY |
| WOS记录号 | WOS:001080441800013 |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/21111]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Song, Jiajun |
| 作者单位 | Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, 6 Kexueyuan South Rd, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Song, Jiajun,Li, Zhuo,Min, Weiqing,et al. Towards Food Image Retrieval via Generalization-Oriented Sampling and Loss Function Design[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2024,20(1):19. |
| APA | Song, Jiajun,Li, Zhuo,Min, Weiqing,&Jiang, Shuqiang.(2024).Towards Food Image Retrieval via Generalization-Oriented Sampling and Loss Function Design.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,20(1),19. |
| MLA | Song, Jiajun,et al."Towards Food Image Retrieval via Generalization-Oriented Sampling and Loss Function Design".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 20.1(2024):19. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。