Search alternatives:
largest decrease » larger decrease (Expand Search), marked decrease (Expand Search)
teer decrease » greater decrease (Expand Search)
nn decrease » _ decrease (Expand Search), a decrease (Expand Search), gy decreased (Expand Search)
largest decrease » larger decrease (Expand Search), marked decrease (Expand Search)
teer decrease » greater decrease (Expand Search)
nn decrease » _ decrease (Expand Search), a decrease (Expand Search), gy decreased (Expand Search)
-
1901
GSConv module structure diagram.
Published 2025“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”
-
1902
Performance comparison of three loss functions.
Published 2025“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”
-
1903
mAP0.5 Curves of various models.
Published 2025“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”
-
1904
Network loss function change diagram.
Published 2025“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”
-
1905
Comparative diagrams of different indicators.
Published 2025“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”
-
1906
YOLOv8n structure diagram.
Published 2025“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”
-
1907
Geometric model of the binocular system.
Published 2025“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”
-
1908
Enhanced dataset sample images.
Published 2025“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”
-
1909
-
1910
-
1911
-
1912
-
1913
-
1914
-
1915
-
1916
-
1917
-
1918
-
1919
-
1920