A Deep Transfer Learning Solution for Food Material Recognition Using Electronic Scales

Xiao, Guangyi; Wu, Qi; Chen, Hao; Da, Da; Guo, Jingzhi; Gong, Zhiguo

doi:10.1109/tii.2019.2931148

Cited by 24 publications

(17 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is also work to recognize gestures by combining some functions in Internet of Things (IoT) [25]. In addition to the vehicle environment, CNN also has a wide range of applications in other fields, such as Smart City [26][27][28], health care [29,30], and transportation [31].What is more, network routing protocols are constantly being improved [32][33][34], and the progress of sensor networks [35][36][37] has greatly improved the reliability of IoT [38][39][40].…”

Section: Wireless Communications and Mobile Computingmentioning

confidence: 99%

A Real-Time Garbage Truck Supervision and Data Statistics Method Based on Object Detection

Zhang

Gao

Xiao

et al. 2020

Wireless Communications and Mobile Computing

Self Cite

View full text Add to dashboard Cite

Garbage classification is difficult to supervise in the stage of collection and transportation. This paper proposes a computer vision-based method for intelligent supervision and workload statistics of garbage trucks. In terms of hardware, this paper deploys a camera and an image processing unit with NPU based on the original on-board computing and communication equipment. In terms of software, this paper uses the YOLOv3-tiny algorithm on the image processing unit to perform real-time target detection on garbage truck work, collects statistics on the color, specifications, and quantity of garbage bins cleaned by the garbage truck, and uploads the results to the server for recording and display. The proposed method has low deployment and maintenance costs while maintaining excellent accuracy and real-time performance, which makes it have good commercial application value.

show abstract

Section: Wireless Communications and Mobile Computingmentioning

confidence: 99%

A Real-Time Garbage Truck Supervision and Data Statistics Method Based on Object Detection

Zhang

Gao

Xiao

et al. 2020

Wireless Communications and Mobile Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our NI-UDA assume the non-shared classes space is known, but it still has big challenges on transfer learning on sparse shared classes in either domain and how to borrow knowledge from non-shared classes while without the negative transfer effect. Label shift [20] is more challenging than traditional UDA and common for real-world application [10]. The potential label shift, which cause conditional feature distributions alignment become more difficult [21].…”

Section: Related Workmentioning

confidence: 99%

“…Traditional UDA either ignores [7] or automatically deletes non-shared big data [8], [9], which can no longer meet the requirements of effective supervision of data utilization and adaptation of massive complex data in the era of big data. As more and more intelligent decisionmaking tasks of smart devices and services are subdivided by the industry, the problem of the difference between the distribution of source big data with large-scale non-shared and imbalanced classes and the distribution of subdivision task data with specified small-and-imbalanced classes has become increasingly prominent, which has become an urgent need one of the research problem to be solved [10].…”

Section: Introductionmentioning

confidence: 99%

“…For non-shared and imbalanced big data and small application tasks in domain adaptation, we mainly analyze the major needs of two typical industrial requirements. (1) Catering big data analysis [10], such as domain adaptation from food material big data to small tasks of restaurant identification. The task of automatic identification of food categories by electronic scales has main challenges: 1) transfer from the laboratory to the real environment, and 2) imbalance of food data.…”

Section: Introductionmentioning

confidence: 99%

“…The previous work of TAN [10] learned from K-classes in the source domain, ignoring the negative transfer effects brought about by these non-shared classes, that is, error accumulation [11] and uncertainty propagation [12]. In order to solve the challenge of knowledge sharing from non-shared data without negative transfer effect, we propose a Source Classifier Filter (SCF) mechanism to filter non-shared data with a fixed confidence threshold of source classifier in feature enhance layer.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

NI-UDA: Graph Adversarial Domain Adaptation from Non-shared-and-Imbalanced Big Data to Small Imbalanced Applications

Xiao¹,

Xiang

Huan

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We propose a new general Graph Adversarial Domain Adaptation (GADA) based on semantic knowledge reasoning of class structure for solving the problem of unsupervised domain adaptation (UDA) from the big data with non-shared and imbalanced classes to specified small and imbalanced applications (NI-UDA), where non-shared classes mean the label space out of the target domain. Our goal is to leverage priori hierarchy knowledge to enhance domain adversarial aligned feature representation with graph reasoning. In this paper, to address two challenges in NI-UDA, we equip adversarial domain adaptation with Hierarchy Graph Reasoning (HGR) layer and the Source Classifier Filter (SCF). For sparse classes transfer challenge, our HGR layer can aggregate local feature to hierarchy graph nodes by node prediction and enhance domain adversarial aligned feature with hierarchy graph reasoning for sparse classes. Our HGR contributes to learn direct semantic patterns for sparse classes by hierarchy attention in self-attention, non-linear mapping and graph normalization. our SCF is proposed for the challenge of knowledge sharing from non-shared data without negative transfer effect by filtering low-confidence non-shared data in HGR layer. Experiments on two benchmark datasets show our GADA methods consistently improve the state-of-theart adversarial UDA algorithms, e.g. GADA(HGR) can greatly improve f1 of the MDD by 7.19% and GVB-GD by 7.89% respectively on imbalanced source task in Meal300 dataset. The code is available at https://gadatransfer.wixsite.com/gada.

show abstract

Multi-food detection using a modified swin-transfomer with recursive feature pyramid network

Lee,

Khanum,

Kumar

2023

Multimed Tools Appl

View full text Add to dashboard Cite

A Deep Transfer Learning Solution for Food Material Recognition Using Electronic Scales

Cited by 24 publications

References 25 publications

A Real-Time Garbage Truck Supervision and Data Statistics Method Based on Object Detection

A Real-Time Garbage Truck Supervision and Data Statistics Method Based on Object Detection

NI-UDA: Graph Adversarial Domain Adaptation from Non-shared-and-Imbalanced Big Data to Small Imbalanced Applications

Multi-food detection using a modified swin-transfomer with recursive feature pyramid network

Contact Info

Product

Resources

About