Comparison between AL and randomly selected data. by Jia Li (160557)

“…This paper introduces a novel classification algorithm, ASGBC, intended to tackle related challenges in diagnosing gallbladder cancer using B-ultrasound images. …”

Framework of MsHop. by Jia Li (160557)

“…This paper introduces a novel classification algorithm, ASGBC, intended to tackle related challenges in diagnosing gallbladder cancer using B-ultrasound images. …”

Variable convolution process. by Jiexiang Yang (19980594)

“…<div><p>Road crack detection is critical to global infrastructure maintenance and public safety, and complex background environments and nonlinear damage crack patterns challenge the need for real-time, efficient, and accurate detection.This paper proposes a lightweight yet robust Flexi-YOLO model based on the YOLOv8 algorithm. We designed Wise-IoU as the model’s loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. …”

GAM structure diagram. by Jiexiang Yang (19980594)

“…<div><p>Road crack detection is critical to global infrastructure maintenance and public safety, and complex background environments and nonlinear damage crack patterns challenge the need for real-time, efficient, and accurate detection.This paper proposes a lightweight yet robust Flexi-YOLO model based on the YOLOv8 algorithm. We designed Wise-IoU as the model’s loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. …”

Hyperparameter settings. by Jiexiang Yang (19980594)

“…<div><p>Road crack detection is critical to global infrastructure maintenance and public safety, and complex background environments and nonlinear damage crack patterns challenge the need for real-time, efficient, and accurate detection.This paper proposes a lightweight yet robust Flexi-YOLO model based on the YOLOv8 algorithm. We designed Wise-IoU as the model’s loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. …”

Ghost detect module. by Jiexiang Yang (19980594)

“…<div><p>Road crack detection is critical to global infrastructure maintenance and public safety, and complex background environments and nonlinear damage crack patterns challenge the need for real-time, efficient, and accurate detection.This paper proposes a lightweight yet robust Flexi-YOLO model based on the YOLOv8 algorithm. We designed Wise-IoU as the model’s loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. …”

Example of preprocessed image. by Jiexiang Yang (19980594)

“…<div><p>Road crack detection is critical to global infrastructure maintenance and public safety, and complex background environments and nonlinear damage crack patterns challenge the need for real-time, efficient, and accurate detection.This paper proposes a lightweight yet robust Flexi-YOLO model based on the YOLOv8 algorithm. We designed Wise-IoU as the model’s loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. …”

Thermodynamic chart. by Jiexiang Yang (19980594)

“…<div><p>Road crack detection is critical to global infrastructure maintenance and public safety, and complex background environments and nonlinear damage crack patterns challenge the need for real-time, efficient, and accurate detection.This paper proposes a lightweight yet robust Flexi-YOLO model based on the YOLOv8 algorithm. We designed Wise-IoU as the model’s loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. …”

Results of ablation study. by Jia Li (160557)

“…This paper introduces a novel classification algorithm, ASGBC, intended to tackle related challenges in diagnosing gallbladder cancer using B-ultrasound images. …”

Principle of ghost convolution. by Jiexiang Yang (19980594)

“…<div><p>Road crack detection is critical to global infrastructure maintenance and public safety, and complex background environments and nonlinear damage crack patterns challenge the need for real-time, efficient, and accurate detection.This paper proposes a lightweight yet robust Flexi-YOLO model based on the YOLOv8 algorithm. We designed Wise-IoU as the model’s loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. …”

Kappa consistency ranges. by Jia Li (160557)

“…This paper introduces a novel classification algorithm, ASGBC, intended to tackle related challenges in diagnosing gallbladder cancer using B-ultrasound images. …”

mAP comparison. by Jiexiang Yang (19980594)

“…<div><p>Road crack detection is critical to global infrastructure maintenance and public safety, and complex background environments and nonlinear damage crack patterns challenge the need for real-time, efficient, and accurate detection.This paper proposes a lightweight yet robust Flexi-YOLO model based on the YOLOv8 algorithm. We designed Wise-IoU as the model’s loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. …”

Actual inspection image. by Jiexiang Yang (19980594)

“…<div><p>Road crack detection is critical to global infrastructure maintenance and public safety, and complex background environments and nonlinear damage crack patterns challenge the need for real-time, efficient, and accurate detection.This paper proposes a lightweight yet robust Flexi-YOLO model based on the YOLOv8 algorithm. We designed Wise-IoU as the model’s loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. …”

Performance metrics under different noise levels. by Jia Li (160557)

“…This paper introduces a novel classification algorithm, ASGBC, intended to tackle related challenges in diagnosing gallbladder cancer using B-ultrasound images. …”

Comparative experiments. by Jiexiang Yang (19980594)

“…<div><p>Road crack detection is critical to global infrastructure maintenance and public safety, and complex background environments and nonlinear damage crack patterns challenge the need for real-time, efficient, and accurate detection.This paper proposes a lightweight yet robust Flexi-YOLO model based on the YOLOv8 algorithm. We designed Wise-IoU as the model’s loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. …”

C2f Module. by Jiexiang Yang (19980594)

“…<div><p>Road crack detection is critical to global infrastructure maintenance and public safety, and complex background environments and nonlinear damage crack patterns challenge the need for real-time, efficient, and accurate detection.This paper proposes a lightweight yet robust Flexi-YOLO model based on the YOLOv8 algorithm. We designed Wise-IoU as the model’s loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. …”

Model generalization experiment. by Jiexiang Yang (19980594)

“…<div><p>Road crack detection is critical to global infrastructure maintenance and public safety, and complex background environments and nonlinear damage crack patterns challenge the need for real-time, efficient, and accurate detection.This paper proposes a lightweight yet robust Flexi-YOLO model based on the YOLOv8 algorithm. We designed Wise-IoU as the model’s loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. …”

Variable convolution Kernel structure diagram. by Jiexiang Yang (19980594)

“…<div><p>Road crack detection is critical to global infrastructure maintenance and public safety, and complex background environments and nonlinear damage crack patterns challenge the need for real-time, efficient, and accurate detection.This paper proposes a lightweight yet robust Flexi-YOLO model based on the YOLOv8 algorithm. We designed Wise-IoU as the model’s loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. …”

Results of ablation study. by Jia Li (160557)

“…This paper introduces a novel classification algorithm, ASGBC, intended to tackle related challenges in diagnosing gallbladder cancer using B-ultrasound images. …”

Effect of active learning. by Jia Li (160557)

“…This paper introduces a novel classification algorithm, ASGBC, intended to tackle related challenges in diagnosing gallbladder cancer using B-ultrasound images. …”