Multi-state Ingredient Recognition via Adaptive Multi-centric Network

doi:10.1109/TII.2023.3333935

CSpace

	Multi-state Ingredient Recognition via Adaptive Multi-centric Network
	Wen, Min 1,2; Song, Jiajun 1,2; Min, Weiqing 1,2; Xiao, Weimin 3; Han, Lin 3; Jiang, Shuqiang 1,2
	2023-12-14
发表期刊	IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
ISSN	1551-3203
页码	10
摘要	Ingredient recognition has received significant attention due to its numerous industrial applications, such as intelligent retail terminals and intelligent cooking devices. However, ingredient recognition has the following challenges: 1) dynamic changes in the number of categories; 2) greater diversity and regionality of ingredients; and 3) large visual differences among different states of ingredients. In this article, we propose an adaptive multi-centric network (AdMNet) to solve the problem of ingredient recognition. AdMNet is based on the idea of retrieval, which consists of two main parts, the adaptive multi-centric nearest-neighbor central mean (AdM-NCM) classifier, and the context-aware attentional pooling (CAP) module. The AdM-NCM classifier adaptively establishes category-centric vector groups to recognize ingredients via optimizing the minimum clustering variance, where each state of the ingredient has its corresponding centric vector. The CAP module combines contextual information and multiple attention mechanisms. It captures more focused and discriminative features with higher weights assigned to fine-grained features, which results in better feature representation. In addition, we collect a large-scale ingredient dataset, ISIA Ingredient-201 with 201 classes and 100 442 images. To prove the greater robustness and generalization of our method, we compare the metrics in basic scenarios and realistic scenarios with those of other methods. Specifically, the base scenario is the regular setup, and the real scenario is similar to the class incremental learning setup. The experimental results show that our method reaches the state of the art on both basic scenarios and realistic scenarios with small samples.
关键词	Ingredient recognition intelligent cooking device
DOI	10.1109/TII.2023.3333935
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China
WOS研究方向	Automation & Control Systems ; Computer Science ; Engineering
WOS类目	Automation & Control Systems ; Computer Science, Interdisciplinary Applications ; Engineering, Industrial
WOS记录号	WOS:001129741500001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38452
专题	中国科学院计算技术研究所
通讯作者	Min, Weiqing
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Versuni, Shanghai 200072, Peoples R China
推荐引用方式 GB/T 7714	Wen, Min,Song, Jiajun,Min, Weiqing,et al. Multi-state Ingredient Recognition via Adaptive Multi-centric Network[J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,2023:10.
APA	Wen, Min,Song, Jiajun,Min, Weiqing,Xiao, Weimin,Han, Lin,&Jiang, Shuqiang.(2023).Multi-state Ingredient Recognition via Adaptive Multi-centric Network.IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,10.
MLA	Wen, Min,et al."Multi-state Ingredient Recognition via Adaptive Multi-centric Network".IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2023):10.