YOLOv8n-BWG model structure diagram. by Yaojun Zhang (389482)

“…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%. …”

BiFormer structure diagram. by Yaojun Zhang (389482)

“…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%. …”

YOLOv8n-BWG detection results diagram. by Yaojun Zhang (389482)

“…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%. …”

GSConv module structure diagram. by Yaojun Zhang (389482)

“…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%. …”

mAP0.5 Curves of various models. by Yaojun Zhang (389482)

“…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%. …”

Network loss function change diagram. by Yaojun Zhang (389482)

“…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%. …”

Comparative diagrams of different indicators. by Yaojun Zhang (389482)

“…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%. …”

YOLOv8n structure diagram. by Yaojun Zhang (389482)

“…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%. …”

Geometric model of the binocular system. by Yaojun Zhang (389482)

“…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%. …”

Enhanced dataset sample images. by Yaojun Zhang (389482)

“…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%. …”

On a steepening environmental gradient, a sharp and stable range margin forms near the expansion threshold. by Jitka Polechová (5400749)

“…(<b>b</b>) As the environmental gradient steepens, the frequency of limited adaptation within the metapopulation increases (black and grey), and hence neutral variation decreases (blue). The black line gives the proportion of demes with limited adaptation after 50,000 generations, when the range margin appears stable; grey gives the proportion after 40,000 generations (depicted is an average over a sliding window of 15 demes). …”

Course of T_body of a female pup before, during and after a thunderstorm. by Nicola Erdsack (443390)

“…</b>: The thunderstorm stopped but it still rained on. <b>5:50 p.m.</b>: T_air = 19.7°C. T_body had decreased by 0.7°C to 36.9°C. …”

Simulation Parameter Settings. by Jinrong Liang (3918740)

“…After applying Taylor pruning to the model, its floating-point operations (FLOPs) were reduced from 40.5 M to 9.5 M, and its parameter memory was decreased from 2.6 M to 0.5 M. …”

Complexity analysis of each model. by Jinrong Liang (3918740)

“…After applying Taylor pruning to the model, its floating-point operations (FLOPs) were reduced from 40.5 M to 9.5 M, and its parameter memory was decreased from 2.6 M to 0.5 M. …”

Radon transform of the constellation diagram. by Jinrong Liang (3918740)

“…After applying Taylor pruning to the model, its floating-point operations (FLOPs) were reduced from 40.5 M to 9.5 M, and its parameter memory was decreased from 2.6 M to 0.5 M. …”

The process of Taylor score pruning. by Jinrong Liang (3918740)

“…After applying Taylor pruning to the model, its floating-point operations (FLOPs) were reduced from 40.5 M to 9.5 M, and its parameter memory was decreased from 2.6 M to 0.5 M. …”

The principle of Radon transformation. by Jinrong Liang (3918740)

“…After applying Taylor pruning to the model, its floating-point operations (FLOPs) were reduced from 40.5 M to 9.5 M, and its parameter memory was decreased from 2.6 M to 0.5 M. …”

Ring constellation diagram. by Jinrong Liang (3918740)

“…After applying Taylor pruning to the model, its floating-point operations (FLOPs) were reduced from 40.5 M to 9.5 M, and its parameter memory was decreased from 2.6 M to 0.5 M. …”

Importance of the features. by Zhi Jiang (269212)

Variable selection in the RF algorithm. by Zhi Jiang (269212)