Yancun Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yancun Yang has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Guorui Sheng
Ludong University
8 shared publications - Shuqiang Jiang
University of Chinese Academy of Sciences, Beijing, China
6 shared publications - Weiqing Min
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, University of Chinese Academy of Sciences, Beijing, China, and Institute of Intelligent Computing Technology, Chinese Academy of Sciences, Suzhou, China
6 shared publications - Jingru Song
School of Information and Electrical Engineering, Ludong University, Yantai, China
4 shared publications - Lili Wang
School of Computer Science and Artificial Intelligence, Ludong University, Yantai, China
4 shared publications - Tao Yao
Ludong University
4 shared publications
Latest Publications
- 16 December 2025
- Published by Elsevier in Pattern Recognition
- Vol. 173
LLM-informed global-local contextualization for zero-shot food detection
- 16 December 2025
- Published by Elsevier in Pattern Recognition
- Vol. 173
LLM-informed global-local contextualization for zero-shot food detection
- 16 June 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 292
Channel grouping vision transformer for lightweight fruit and vegetable recognition
- 16 June 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 292
Channel grouping vision transformer for lightweight fruit and vegetable recognition
- Open Access
- 29 October 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (10) , 1-25
Lightweight Food Recognition via Aggregation Block and Feature Encoding
Food image recognition has recently been given considerable attention in the multimedia field in light of its possible implications on health. The characteristics of the dispersed distribution of ingredients in food images put forward higher requirements on the long-range information extraction ability of neural networks, leading to more complex and deeper models. Nevertheless, the lightweight version of food image recognition is essential for improved implementation on end devices and sustained server-side expansion. To address this issue, we present Aggregation Feature Net (AFNet), a lightweight network that is capable of effectively capturing both global and local features from food images. In AFNet, we develop a novel convolution based on a residual model by encoding global features through row-wise and column-wise information integration. Merging aggregation block with classic local convolution yields a framework that works as the backbone of the network. Based on the efficient use of parameters by the aggregation block, we constructed a lightweight food image recognition network with fewer layers and a smaller scale, assisted by a new type of activation function. Experimental results on four popular food recognition datasets demonstrate that our approach achieves state-of-the-art performance with higher accuracy and fewer FLOPs and parameters. For example, in comparison to the current state-of-the-art model of MobileViTv2, AFNet achieved 88.4% accuracy of the top-1 level on the ETHZ Food-101 dataset, with similar parameters and FLOPs but 1.4% more accuracy. The source code will be provided in supplementary materials.
- 29 October 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (10) , 1-25
Open AccessLightweight Food Recognition via Aggregation Block and Feature Encoding
Food image recognition has recently been given considerable attention in the multimedia field in light of its possible implications on health. The characteristics of the dispersed distribution of ingredients in food images put forward higher requirements on the long-range information extraction ability of neural networks, leading to more complex and deeper models. Nevertheless, the lightweight version of food image recognition is essential for improved implementation on end devices and sustained server-side expansion. To address this issue, we present Aggregation Feature Net (AFNet), a lightweight network that is capable of effectively capturing both global and local features from food images. In AFNet, we develop a novel convolution based on a residual model by encoding global features through row-wise and column-wise information integration. Merging aggregation block with classic local convolution yields a framework that works as the backbone of the network. Based on the efficient use of parameters by the aggregation block, we constructed a lightweight food image recognition network with fewer layers and a smaller scale, assisted by a new type of activation function. Experimental results on four popular food recognition datasets demonstrate that our approach achieves state-of-the-art performance with higher accuracy and fewer FLOPs and parameters. For example, in comparison to the current state-of-the-art model of MobileViTv2, AFNet achieved 88.4% accuracy of the top-1 level on the ETHZ Food-101 dataset, with similar parameters and FLOPs but 1.4% more accuracy. The source code will be provided in supplementary materials.
- 2 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on AgriFood Electronics
- Vol. 2 (2) , 392-402
Lightweight Food Image Recognition With Global Shuffle Convolution
Consumer behaviors and habits in food choices impact their physical health and have implications for climate change and global warming. Efficient food image recognition can assist individuals in making more environmentally friendly and healthier dietary choices using end devices, such as smartphones. Simultaneously, it can enhance the efficiency of server-side training, thereby reducing carbon emissions. We propose a lightweight deep neural network named Global Shuffle Net (GSNet) that can efficiently recognize food images. In GSNet, we develop a novel convolution method called global shuffle convolution, which captures the dependence between long-range pixels. Merging global shuffle convolution with classic local convolution yields a framework that works as the backbone of GSNet. Through GSNet's ability to capture the dependence between long-range pixels at the start of the network, by restricting the number of layers in the middle and rear, the parameters and floating operation operations (FLOPs) can be minimized without compromising the performance, thus permitting a lightweight goal to be achieved. Experimental results on four popular food recognition datasets demonstrate that our approach achieves state-of-the-art performance with higher accuracy and fewer FLOPs and parameters. For example, in comparison to the current state-of-the-art model of MobileViTv2, GSNet achieved 87.9% accuracy of the top-1 level on the Eidgenössische Technische Hochschule Zürich (ETHZ) Food-101 dataset with 28% reduction in the parameters, 37% reduction in the FLOPs, but a 0.7% more accuracy.
- 2 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on AgriFood Electronics
- Vol. 2 (2) , 392-402
Lightweight Food Image Recognition With Global Shuffle Convolution
Consumer behaviors and habits in food choices impact their physical health and have implications for climate change and global warming. Efficient food image recognition can assist individuals in making more environmentally friendly and healthier dietary choices using end devices, such as smartphones. Simultaneously, it can enhance the efficiency of server-side training, thereby reducing carbon emissions. We propose a lightweight deep neural network named Global Shuffle Net (GSNet) that can efficiently recognize food images. In GSNet, we develop a novel convolution method called global shuffle convolution, which captures the dependence between long-range pixels. Merging global shuffle convolution with classic local convolution yields a framework that works as the backbone of GSNet. Through GSNet's ability to capture the dependence between long-range pixels at the start of the network, by restricting the number of layers in the middle and rear, the parameters and floating operation operations (FLOPs) can be minimized without compromising the performance, thus permitting a lightweight goal to be achieved. Experimental results on four popular food recognition datasets demonstrate that our approach achieves state-of-the-art performance with higher accuracy and fewer FLOPs and parameters. For example, in comparison to the current state-of-the-art model of MobileViTv2, GSNet achieved 87.9% accuracy of the top-1 level on the Eidgenössische Technische Hochschule Zürich (ETHZ) Food-101 dataset with 28% reduction in the parameters, 37% reduction in the FLOPs, but a 0.7% more accuracy.
- Open Access
A Lightweight Hybrid Model with Location-Preserving ViT for Efficient Food Recognition
Food-image recognition plays a pivotal role in intelligent nutrition management, and lightweight recognition methods based on deep learning are crucial for enabling mobile deployment. This capability empowers individuals to effectively manage their daily diet and nutrition using devices such as smartphones. In this study, we propose an Efficient Hybrid Food Recognition Net (EHFR–Net), a novel neural network that integrates Convolutional Neural Networks (CNN) and Vision Transformer (ViT). We find that in the context of food-image recognition tasks, while ViT demonstrates superiority in extracting global information, its approach of disregarding the initial spatial information hampers its efficacy. Therefore, we designed a ViT method termed Location-Preserving Vision Transformer (LP–ViT), which retains positional information during the global information extraction process. To ensure the lightweight nature of the model, we employ an inverted residual block on the CNN side to extract local features. Global and local features are seamlessly integrated by directly summing and concatenating the outputs from the convolutional and ViT structures, resulting in the creation of a unified Hybrid Block (HBlock) in a coherent manner. Moreover, we optimize the hierarchical layout of EHFR–Net to accommodate the unique characteristics of HBlock, effectively reducing the model size. Our extensive experiments on three well-known food image-recognition datasets demonstrate the superiority of our approach. For instance, on the ETHZ Food–101 dataset, our method achieves an outstanding recognition accuracy of 90.7%, which is 3.5% higher than the state-of-the-art ViT-based lightweight network MobileViTv2 (87.2%), which has an equivalent number of parameters and calculations.
Open AccessA Lightweight Hybrid Model with Location-Preserving ViT for Efficient Food Recognition
Food-image recognition plays a pivotal role in intelligent nutrition management, and lightweight recognition methods based on deep learning are crucial for enabling mobile deployment. This capability empowers individuals to effectively manage their daily diet and nutrition using devices such as smartphones. In this study, we propose an Efficient Hybrid Food Recognition Net (EHFR–Net), a novel neural network that integrates Convolutional Neural Networks (CNN) and Vision Transformer (ViT). We find that in the context of food-image recognition tasks, while ViT demonstrates superiority in extracting global information, its approach of disregarding the initial spatial information hampers its efficacy. Therefore, we designed a ViT method termed Location-Preserving Vision Transformer (LP–ViT), which retains positional information during the global information extraction process. To ensure the lightweight nature of the model, we employ an inverted residual block on the CNN side to extract local features. Global and local features are seamlessly integrated by directly summing and concatenating the outputs from the convolutional and ViT structures, resulting in the creation of a unified Hybrid Block (HBlock) in a coherent manner. Moreover, we optimize the hierarchical layout of EHFR–Net to accommodate the unique characteristics of HBlock, effectively reducing the model size. Our extensive experiments on three well-known food image-recognition datasets demonstrate the superiority of our approach. For instance, on the ETHZ Food–101 dataset, our method achieves an outstanding recognition accuracy of 90.7%, which is 3.5% higher than the state-of-the-art ViT-based lightweight network MobileViTv2 (87.2%), which has an equivalent number of parameters and calculations.
- 2 September 2022
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 37 (12) , 11465-11481
Food recognition via an efficient neural network with transformer grouping
- 2 September 2022
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 37 (12) , 11465-11481
Food recognition via an efficient neural network with transformer grouping
- 1 January 2018
- Published by Elsevier in Physica A: Statistical Mechanics and its Applications
- Vol. 490, 1191-1200
Heterogeneous game resource distributions promote cooperation in spatial prisoner’s dilemma game
- 1 January 2018
- Published by Elsevier in Physica A: Statistical Mechanics and its Applications
- Vol. 490, 1191-1200
Heterogeneous game resource distributions promote cooperation in spatial prisoner’s dilemma game