-
441
mAP comparison.
Published 2025“…Experimental results show that Flexi-YOLO achieves an accuracy increase of 2.7% over YOLOv8n, a recall rate rise of 4.7%, a mAP improvement of 5.3%, a mAP@0.5–0.95 increase of 3.9%, a decrease of 0.5 in GFLOPS, and an F1 score improvement from 0.80 to 0.84. …”
-
442
Actual inspection image.
Published 2025“…Experimental results show that Flexi-YOLO achieves an accuracy increase of 2.7% over YOLOv8n, a recall rate rise of 4.7%, a mAP improvement of 5.3%, a mAP@0.5–0.95 increase of 3.9%, a decrease of 0.5 in GFLOPS, and an F1 score improvement from 0.80 to 0.84. …”
-
443
Comparative experiments.
Published 2025“…Experimental results show that Flexi-YOLO achieves an accuracy increase of 2.7% over YOLOv8n, a recall rate rise of 4.7%, a mAP improvement of 5.3%, a mAP@0.5–0.95 increase of 3.9%, a decrease of 0.5 in GFLOPS, and an F1 score improvement from 0.80 to 0.84. …”
-
444
C2f Module.
Published 2025“…Experimental results show that Flexi-YOLO achieves an accuracy increase of 2.7% over YOLOv8n, a recall rate rise of 4.7%, a mAP improvement of 5.3%, a mAP@0.5–0.95 increase of 3.9%, a decrease of 0.5 in GFLOPS, and an F1 score improvement from 0.80 to 0.84. …”
-
445
Model generalization experiment.
Published 2025“…Experimental results show that Flexi-YOLO achieves an accuracy increase of 2.7% over YOLOv8n, a recall rate rise of 4.7%, a mAP improvement of 5.3%, a mAP@0.5–0.95 increase of 3.9%, a decrease of 0.5 in GFLOPS, and an F1 score improvement from 0.80 to 0.84. …”
-
446
Variable convolution Kernel structure diagram.
Published 2025“…Experimental results show that Flexi-YOLO achieves an accuracy increase of 2.7% over YOLOv8n, a recall rate rise of 4.7%, a mAP improvement of 5.3%, a mAP@0.5–0.95 increase of 3.9%, a decrease of 0.5 in GFLOPS, and an F1 score improvement from 0.80 to 0.84. …”
-
447
-
448
-
449
-
450
-
451
Decoding the Structure–Property–Function Relationships in Covalent Organic Frameworks for Sustainable Battery Design
Published 2025“…Pore decoration of the frameworks with glycol side chains dramatically reduced ion mobility due to increased electrostatic interactions. …”
-
452
Experimental environment and parameters.
Published 2025“…<div><p>In the context of industrial automation, the accurate detection of small defects on bearing surfaces (dents, bruise, scratch) is crucial for the safe operation of equipment. …”
-
453
Results of ablation experiments.
Published 2025“…<div><p>In the context of industrial automation, the accurate detection of small defects on bearing surfaces (dents, bruise, scratch) is crucial for the safe operation of equipment. …”
-
454
ECA structural model diagram.
Published 2025“…<div><p>In the context of industrial automation, the accurate detection of small defects on bearing surfaces (dents, bruise, scratch) is crucial for the safe operation of equipment. …”
-
455
YOLOv5s general structure diagram.
Published 2025“…<div><p>In the context of industrial automation, the accurate detection of small defects on bearing surfaces (dents, bruise, scratch) is crucial for the safe operation of equipment. …”
-
456
Heat maps for different models.
Published 2025“…<div><p>In the context of industrial automation, the accurate detection of small defects on bearing surfaces (dents, bruise, scratch) is crucial for the safe operation of equipment. …”
-
457
Defect category statistics.
Published 2025“…<div><p>In the context of industrial automation, the accurate detection of small defects on bearing surfaces (dents, bruise, scratch) is crucial for the safe operation of equipment. …”
-
458
CARAFE general structure.
Published 2025“…<div><p>In the context of industrial automation, the accurate detection of small defects on bearing surfaces (dents, bruise, scratch) is crucial for the safe operation of equipment. …”
-
459
ECN-YOLOv5s structure diagram.
Published 2025“…<div><p>In the context of industrial automation, the accurate detection of small defects on bearing surfaces (dents, bruise, scratch) is crucial for the safe operation of equipment. …”
-
460
Qualitative Examples of Corrected Sentences.
Published 2025“…This study proposes an enhanced model based on Bidirectional Encoder Representations from Transformers (BERT), combined with a dependency self-attention mechanism, to automatically detect and correct textual errors in the translation process. …”