Robust Traffic Prediction From Spatial–Temporal Data Based on Conditional Distribution Learning

Zeng, Zeng; Zhao, Wei; Qian, Peisheng; Zhou, Yingjie; Zhao, Ziyuan; Chen, Cen; Guan, Cuntai

doi:10.1109/tcyb.2021.3131285

Cited by 19 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach significantly reduces the impact of label ambiguity on the results. Hence its introduction, LDL has gained significant attention in the realm of deep learning and has been successfully implemented in diverse domains, such as facial expression recognition [37], traffic prediction [38], and facial age estimation [39], [40]. Zhou et al [37] presented an innovative approach to facial expression recognition by introducing emotional distribution learning.…”

Section: B Label Distribution Learningmentioning

confidence: 99%

KDALDL: Knowledge Distillation-Based Adaptive Label Distribution Learning Network for Bone Age Assessment

Zheng,

Yu,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Deep learning-based bone age assessment (BAA) approaches have certain drawbacks, such as ignoring the correlation of age labels and simply assuming that bone development is linearly related to bone age, which can affect the accuracy of predictions. To solve these problems, a knowledge distillationbased adaptive label distribution learning method called KDALDL is proposed. The KDALDL framework comprises a teacher model and a student model, both consisting of modules for multi-scale feature extraction, feature refinement, and label distribution learning. First, a multi-scale feature extraction module is designed based on the swin transformer to extract feature information at various scales. Subsequently, these features are fed into the feature refinement module to capture the optimal image features. Then, the discrete labels obtained from the age labels through the Gaussian formula are used to train the teacher model. Finally, the teacher model's outputs are used to train the student model through the knowledge distillation technique, which enables the student model to achieve improved results by learning from the teacher model. The proposed method is validated using the Radiological Society of North America (RSNA) dataset, which exhibits outstanding results.INDEX TERMS Bone age assessment, Knowledge distillation, Label distribution learning, Swin transformer.

show abstract

Section: B Label Distribution Learningmentioning

confidence: 99%

KDALDL: Knowledge Distillation-Based Adaptive Label Distribution Learning Network for Bone Age Assessment

Zheng,

Yu,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…On the other hand, label distribution learning (LDL) was proposed to distinguish label ambiguity, which is challenging. [8,25]. In LDL, a label distribution can be assigned to an sample.…”

Section: Related Workmentioning

confidence: 99%

“…Under particular circumstances, mean loss and variance loss contradict each other and prevent the accurate prediction to be achieved. In [8], residue loss was proposed to penalize residue errors of the long tails in the distribution for traffic prediction. We advanced the mean-residue loss in an adaptive manner for robust facial age estimation.…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, the top-K accuracy of deep learning models has achieved a very high level, e.g., the best top-5 accuracy on the ImageNet dataset is 98% [7]. In age estimation, we can assume that y i is included in top-K classes and the ages out of top-K have a very limited correlation with y i , and then the sum of out-of-top-K probabilities can be treated as residue [8]. However, how to determine K remains a problem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Mean-Residue Loss for Robust Facial Age Estimation

Zhao¹,

Qian²,

Hou³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Automated facial age estimation has diverse real-world applications in multimedia analysis, e.g., video surveillance, and human-computer interaction. However, due to the randomness and ambiguity of the aging process, age assessment is challenging. Most research work over the topic regards the task as one of age regression, classification, and ranking problems, and cannot well leverage age distribution in representing labels with age ambiguity. In this work, we propose a simple yet effective loss function for robust facial age estimation via distribution learning, i.e., adaptive meanresidue loss, in which, the mean loss penalizes the difference between the estimated age distribution's mean and the ground-truth age, whereas the residue loss penalizes the entropy of age probability out of dynamic top-K in the distribution. Experimental results in the datasets FG-NET and CLAP2016 have validated the effectiveness of the proposed loss. Our code is available at https://github.com/ jacobzhaoziyuan/AMR-Loss.

show abstract

“…Researchers from Computer Science, Neuroscience, and Medical fields have applied EEG-based Brain-Computer Interaction (BCI) techniques in many different ways [2,15,19,22,24,26,34], such as diagnosis of abnormal states, evaluating the effect of the treatments, seizure detection, motor imagery tasks [4,5,6,17,23,27], and developing BCI-based games [14]. Previous studies have demonstrated the great potential of machine learning, deep learning, and transfer learning algorithms [1,3,7,8,12,16,18,20,21,25,28,29,37,38,39,40,41,42] in such clinical and non-clinical data analysis.…”

Section: Introductionmentioning

confidence: 99%

Time Majority Voting, a PC-based EEG Classifier for Non-expert Users

Dou¹,

Zhang²,

Qu³

2022

Preprint

View full text Add to dashboard Cite

Using Machine Learning and Deep Learning to predict cognitive tasks from electroencephalography (EEG) signals is a rapidly advancing field in Brain-Computer Interfaces (BCI). In contrast to the fields of computer vision and natural language processing, the data amount of these trials is still rather tiny. Developing a PC-based machine learning technique to increase the participation of non-expert end-users could help solve this data collection issue. We created a novel algorithm for machine learning called Time Majority Voting (TMV). In our experiment, TMV performed better than cutting-edge algorithms. It can operate efficiently on personal computers for classification tasks involving the BCI. These interpretable data also assisted end-users and researchers in comprehending EEG tests better.

show abstract

Robust Traffic Prediction From Spatial–Temporal Data Based on Conditional Distribution Learning

Cited by 19 publications

References 35 publications

KDALDL: Knowledge Distillation-Based Adaptive Label Distribution Learning Network for Bone Age Assessment

KDALDL: Knowledge Distillation-Based Adaptive Label Distribution Learning Network for Bone Age Assessment

Adaptive Mean-Residue Loss for Robust Facial Age Estimation

Time Majority Voting, a PC-based EEG Classifier for Non-expert Users

Contact Info

Product

Resources

About