Jiqing Li

Dr. Jiqing Li

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 May 2023 in Agriculture
Verified
Journal Article
Open access
PDF file
DLDasen Li
Dasen Li
ZYZhendong Yin
Zhendong Yin
YZYanlong Zhao
Yanlong Zhao
WZWudi Zhao
Wudi Zhao
JLJiqing Li
Jiqing Li
Tomato disease classification based on images of leaves has received wide attention recently. As one of the best tomato disease classification methods, the convolutional neural network (CNN) has an immense impact due to its impressive performance. However, better performance is verified by independent identical distribution (IID) samples of tomato disease, which breaks down dramatically on out-of-distribution (OOD) classification tasks. In this paper, we investigated the corruption shifts, which was a vital component of OOD, and proposed a tomato disease classification method to improve the performance of corruption shift generalization. We first adopted discrete cosine transform (DCT) to obtain the low-frequency components. Then, the weight of the feature map was calculated by multiple low-frequency components, in order to reduce the influence of high-frequency variation caused by corrupted perturbation. The proposed method, termed as a multiple low-frequency attention network (MLFAnet), was verified by the benchmarking of ImageNet-C. The accuracy result and generalization performance confirmed the effectiveness of MLFAnet. The satisfactory generalization performance of our proposed classification method provides a reliable tool for the diagnosis of tomato disease.

8 June 2023 in Preprints.org
Verified
Preprint
Open access
PDF file
JLJiqing Li
Jiqing Li
ZYZhendong Yin
Zhendong Yin
DLDasen Li
Dasen Li
YZYanlong Zhao
Yanlong Zhao
Crop disease classification has always been a critical and persistent problem in the field of agricultural and forestry sciences, where often we do not have access to a sufficient number of samples to know the distribution of real-world samples. How to make full use of the existing data is the starting point of our thinking. To address this problem, this paper proposes a supervised image augmentation method Negative Contrast, which uses the contrast images of existing disease samples after removing disease areas as negative samples for image augmentation when samples are relatively scarce. Numerous experiments have shown that several classical models using this augmentation method have improved in disease classification of four crops, rice, wheat, corn, and soybean, with a maximum accuracy improvement of 30.8%. In addition, the comparative analysis of attentional heat map shows that the model using Negative Contrast is more accurate and intense on the area of interest of diseases, and thus reflects better generalization ability in real-world disease classification. Our dataset and codes can be found in https://www.kaggle.com/datasets/w970704112/corn-wheat-rice-soybean and https://github.com/hiter0/contrastaug .

24 July 2023 in Agriculture
Verified
Journal Article
Open access
PDF file
JLJiqing Li
Jiqing Li
ZYZhendong Yin
Zhendong Yin
DLDasen Li
Dasen Li
YZYanlong Zhao
Yanlong Zhao
Crop disease classification constitutes a significant and longstanding challenge in the domain of agricultural and forestry sciences. Frequently, there is an insufficient number of samples to accurately discern the distribution of real-world instances. Leveraging the full potential of the available data is the genesis of our approach. To address this issue, we propose a supervised image augmentation technique—Negative Contrast. This method employs contrast images of existing disease samples, devoid of disease areas, as negative samples for image augmentation, particularly when the samples are relatively scarce. Numerous experiments demonstrate that the employment of this augmentation method enhances the disease classification performance of several classical models across four crops—rice, wheat, corn, and soybean, with an accuracy improvement reaching up to 30.8%. Furthermore, the comparative analysis of attentional heatmaps reveals that models utilizing negative contrast focus more accurately and intensely on the disease regions of interest, thereby exhibiting superior generalization capabilities in real-world crop disease classification.

19 May 2023
Verified
Conference Paper
Open access
JZJiayin Zhang
Jiayin Zhang
ZYZhendong Yin
Zhendong Yin
DLDasen Li
Dasen Li
JLJiqing Li
Jiqing Li
Food crops are very important to people's production and life, and intelligent recognition of food crop disease images is of great significance. However, in the natural environment, the health and disease samples of food crops often have a long-tailed distribution. Long-tailed data is a difficult point for image classification, and insufficient training of tail data often occurs. In this paper, based on transfer learning, the Bilateral-Branch Network is used as the framework to solve the long-tailed recognition problem. Meanwhile, three re-sampling strategies are designed for the Bilateral-Branch Network: balanced re-sampling, smooth reverse re-sampling and reverse re-sampling. After that, we conduct comparative experiments with different model structures and different re-sampling strategies. Finally, we get the conclusion that the Bilateral-Branch Network can effectively solve the long-tailed recognition problem. Among several re-sampling strategies, reverse re-sampling gives the best results. The best result of our method on the long-tailed dataset of food crop disease images is 94.3%, which is 0.7 percentage points higher than that of the traditional single-branch network model under the same conditions.

3 July 2025 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
JLJiqing Li
Jiqing Li
ZYZhendong Yin
Zhendong Yin
DLDasen Li
Dasen Li
YZYanlong Zhao
Yanlong Zhao
In the domain of deep learning for visual tasks, ensemble models combine several less accurate models to form a more precise composite model, improving overall performance. Traditionally, majority voting and average probabilities have been the main decision-making techniques in ensemble learning, focusing only on the TOP1 Class of base models, hence overlooking other significant information. This article introduces a new algorithm, TOP2 hybrid decision (TOP2 HD), which enhances the TOP1 accuracy of the ensemble model. TOP2 HD categorizes base models into hierarchies based on their TOP1 Class and uses the TOP2 Class for ranking, leading to better performance. Extensive experiments across various models and datasets demonstrate that TOP2 HD not only surpasses traditional ensemble methods, such as majority voting, average probabilities, and stacking, but also exceeds many of the latest ensemble strategies in the image domain. In addition, our experiments revealed a functional relationship between the test accuracy of the ensemble model and the number of base models. This enables us to predict the upper limit of the ensemble model’s performance using only a fraction of the models, providing a crucial reference for the performance after the deployment of the ensemble model.