ASAHI adaptively slices high-res images into 6 or 12 patches, adds slicing-assisted fine-tuning, and uses Cluster-DIoU-NMS to hit 56.8% mAP on VisDrone2019 and 22.7% on xView while running 20-25% faster than fixed slicing baselines.
PP-YOLOE: An evolved version of YOLO
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
YOLOv11 delivers higher mean average precision on standard benchmarks than prior YOLO versions while keeping real-time inference speed through C3K2, SPPF, and C2PSA modules.
citing papers explorer
-
Adaptive Slicing-Assisted Hyper Inference for Enhanced Small Object Detection in High-Resolution Imagery
ASAHI adaptively slices high-res images into 6 or 12 patches, adds slicing-assisted fine-tuning, and uses Cluster-DIoU-NMS to hit 56.8% mAP on VisDrone2019 and 22.7% on xView while running 20-25% faster than fixed slicing baselines.
-
YOLOv11 Demystified: A Practical Guide to High-Performance Object Detection
YOLOv11 delivers higher mean average precision on standard benchmarks than prior YOLO versions while keeping real-time inference speed through C3K2, SPPF, and C2PSA modules.