Search alternatives:
significant decrease » significant increase (Expand Search), significantly increased (Expand Search)
small decrease » small increased (Expand Search)
point decrease » point increase (Expand Search)
significant decrease » significant increase (Expand Search), significantly increased (Expand Search)
small decrease » small increased (Expand Search)
point decrease » point increase (Expand Search)
-
61
-
62
-
63
-
64
-
65
-
66
-
67
-
68
Architecture of Swin-T model.
Published 2024“…Experimental results demonstrate that compared to the baseline model, the proposed enhanced model achieves a reduction of 2.5G Flops computational complexity and a 16% speed improvement on a private pavement disease dataset, with only a 1.2 percentage point decrease in AUC accuracy. Moreover, compared to other mainstream image classification models, this model exhibits more balanced performance on a public dataset, with improved accuracy and speed that better align with the practical requirements of pavement inspection. …”
-
69
Model the experimental results curve.
Published 2024“…Experimental results demonstrate that compared to the baseline model, the proposed enhanced model achieves a reduction of 2.5G Flops computational complexity and a 16% speed improvement on a private pavement disease dataset, with only a 1.2 percentage point decrease in AUC accuracy. Moreover, compared to other mainstream image classification models, this model exhibits more balanced performance on a public dataset, with improved accuracy and speed that better align with the practical requirements of pavement inspection. …”
-
70
Results of comparison experiments.
Published 2024“…Experimental results demonstrate that compared to the baseline model, the proposed enhanced model achieves a reduction of 2.5G Flops computational complexity and a 16% speed improvement on a private pavement disease dataset, with only a 1.2 percentage point decrease in AUC accuracy. Moreover, compared to other mainstream image classification models, this model exhibits more balanced performance on a public dataset, with improved accuracy and speed that better align with the practical requirements of pavement inspection. …”
-
71
Architecture of Swin Transformer Block.
Published 2024“…Experimental results demonstrate that compared to the baseline model, the proposed enhanced model achieves a reduction of 2.5G Flops computational complexity and a 16% speed improvement on a private pavement disease dataset, with only a 1.2 percentage point decrease in AUC accuracy. Moreover, compared to other mainstream image classification models, this model exhibits more balanced performance on a public dataset, with improved accuracy and speed that better align with the practical requirements of pavement inspection. …”
-
72
Disease distribution map of the GZDL-BD.
Published 2024“…Experimental results demonstrate that compared to the baseline model, the proposed enhanced model achieves a reduction of 2.5G Flops computational complexity and a 16% speed improvement on a private pavement disease dataset, with only a 1.2 percentage point decrease in AUC accuracy. Moreover, compared to other mainstream image classification models, this model exhibits more balanced performance on a public dataset, with improved accuracy and speed that better align with the practical requirements of pavement inspection. …”
-
73
Token merging module.
Published 2024“…Experimental results demonstrate that compared to the baseline model, the proposed enhanced model achieves a reduction of 2.5G Flops computational complexity and a 16% speed improvement on a private pavement disease dataset, with only a 1.2 percentage point decrease in AUC accuracy. Moreover, compared to other mainstream image classification models, this model exhibits more balanced performance on a public dataset, with improved accuracy and speed that better align with the practical requirements of pavement inspection. …”
-
74
Comparative results of the ablation experiments.
Published 2024“…Experimental results demonstrate that compared to the baseline model, the proposed enhanced model achieves a reduction of 2.5G Flops computational complexity and a 16% speed improvement on a private pavement disease dataset, with only a 1.2 percentage point decrease in AUC accuracy. Moreover, compared to other mainstream image classification models, this model exhibits more balanced performance on a public dataset, with improved accuracy and speed that better align with the practical requirements of pavement inspection. …”
-
75
Data Sheet 1_Iron modulates barrier integrity and stem cell function of small intestine during experimental colitis.docx
Published 2025“…</p>Methods<p>Mice were treated by 2.5% dextran sulfate sodium (DSS) for 7 days to established acute experimental colitis. Small intestinal tissues were collected at different time points in the process of DSS-induced colitis. …”
-
76
Table 3_NK cell-derived extracellular vesicles enhance cytotoxicity and immune cell recruitment in non-small cell lung cancer.xlsx
Published 2025“…Introduction<p>Immune-based agents, especially Immune Checkpoint Inhibitors (ICI), are standard of care therapy in non-small cell lung cancers (NSCLC); however, a significant number of patient tumors fail to respond, or develop resistance. …”
-
77
Table 7_NK cell-derived extracellular vesicles enhance cytotoxicity and immune cell recruitment in non-small cell lung cancer.xlsx
Published 2025“…Introduction<p>Immune-based agents, especially Immune Checkpoint Inhibitors (ICI), are standard of care therapy in non-small cell lung cancers (NSCLC); however, a significant number of patient tumors fail to respond, or develop resistance. …”
-
78
Image 1_NK cell-derived extracellular vesicles enhance cytotoxicity and immune cell recruitment in non-small cell lung cancer.jpg
Published 2025“…Introduction<p>Immune-based agents, especially Immune Checkpoint Inhibitors (ICI), are standard of care therapy in non-small cell lung cancers (NSCLC); however, a significant number of patient tumors fail to respond, or develop resistance. …”
-
79
Table 8_NK cell-derived extracellular vesicles enhance cytotoxicity and immune cell recruitment in non-small cell lung cancer.xlsx
Published 2025“…Introduction<p>Immune-based agents, especially Immune Checkpoint Inhibitors (ICI), are standard of care therapy in non-small cell lung cancers (NSCLC); however, a significant number of patient tumors fail to respond, or develop resistance. …”
-
80
Table 4_NK cell-derived extracellular vesicles enhance cytotoxicity and immune cell recruitment in non-small cell lung cancer.xlsx
Published 2025“…Introduction<p>Immune-based agents, especially Immune Checkpoint Inhibitors (ICI), are standard of care therapy in non-small cell lung cancers (NSCLC); however, a significant number of patient tumors fail to respond, or develop resistance. …”