YOLOX exceeds prior YOLO models by adopting anchor-free detection, decoupled heads, and SimOTA assignment to reach 50.0% AP on COCO for the large variant.
Focal loss for dense object detection
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2roles
background 1polarities
background 1representative citing papers
ATM-Net fuses anatomy-aware text prompts with image features through ATPG, HASF, and CCAE modules to outperform prior methods on fine-grained lumbar spine segmentation in MRSpineSeg and SPIDER datasets.
citing papers explorer
-
YOLOX: Exceeding YOLO Series in 2021
YOLOX exceeds prior YOLO models by adopting anchor-free detection, decoupled heads, and SimOTA assignment to reach 50.0% AP on COCO for the large variant.
-
Anatomy-Aware Text-Visual Fusion with Dual-Perspective Prompts for Fine-Grained Lumbar Spine Segmentation
ATM-Net fuses anatomy-aware text prompts with image features through ATPG, HASF, and CCAE modules to outperform prior methods on fine-grained lumbar spine segmentation in MRSpineSeg and SPIDER datasets.