Channel-pruned YOLOv4 raises detection speed on Trash-ICRA 19 from 15.19 to 19.4 FPS while keeping mAP near 96%, which the authors propose as an efficient model for marine debris detection on low-power hardware.
Cherson, The marine debris research, prevention and reduction act: A policy analysis (2005)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Efficient Object Detection of Marine Debris using Pruned YOLO Model
Channel-pruned YOLOv4 raises detection speed on Trash-ICRA 19 from 15.19 to 19.4 FPS while keeping mAP near 96%, which the authors propose as an efficient model for marine debris detection on low-power hardware.