The AEs and corresponding MSEs of Rényi entropy under different censoring schemes. حسب Qin Gong (118801)

الموضوعات:

The AEs and corresponding MSEs of Shannon entropy under different censoring schemes. حسب Qin Gong (118801)

الموضوعات:

PC-II samples obtained using m = 7 observations. حسب Qin Gong (118801)

الموضوعات:

CDF plots of GIED. حسب Qin Gong (118801)

الموضوعات:

Loss curve. حسب Jiexiang Yang (19980594)

الموضوعات:

Experimental results of various loss functions. حسب Dongshan Jiang (21866339)

"…Then, a CGBD module is proposed in the neck structure to reconstruct the ordinary convolution to improve the feature extraction ability of the model for small targets. Finally, the SIoU loss function is used to replace CIoU to accelerate the convergence of the model. …"

Results of the comparative experiment. حسب Jia Li (160557)

الموضوعات:

Comparison of attention mechanisms. حسب Jia Li (160557)

الموضوعات:

Results of ablation experiments. حسب Jia Li (160557)

الموضوعات:

Comparison of attention mechanisms. حسب Jia Li (160557)

الموضوعات:

Experimental environment configuration. حسب Jia Li (160557)

الموضوعات:

Model comparison experiments. حسب Jia Li (160557)

الموضوعات:

Insulator dataset data enhancement. حسب Jia Li (160557)

الموضوعات:

SPDConv structure diagram. حسب Jia Li (160557)

الموضوعات:

Visualisation and analysis of test results. حسب Jia Li (160557)

الموضوعات:

Comparison of mAP@0.5 and mAP@0.5:0.95 curves. حسب Jia Li (160557)

الموضوعات:

(a) ROAL Accuracies and (b) ROAL label requests per episode for the 1^st, 2^nd, 5^th, and 10^th instances of all classes. حسب Honglan Huang (341951)

الموضوعات:

On the improvement of reinforcement active learning with the involvement of cross entropy to address one-shot learning problem حسب Honglan Huang (341951)

الموضوعات:

Algorithm framework of this paper. حسب Xiaoqin Wu (470428)

"…The standard convolution blocks of the coding path and decoding path on the original network are improved to dense blocks, which enhances the transmission of features. The mixed loss function composed of the Binary Cross Entropy Loss function and the Tversky coefficient is used to replace the original single cross-entropy loss, which restrains the influence of irrelevant features on segmentation accuracy. …"

Optimum solutions and tuning of the dependent variables for various cases based on the PSO technique (standard IEEE 30-bus test network). حسب Abdullah Khan (377292)

الموضوعات: