NMS Strikes Back
Paper • 2212.06137 • Published • 1
How to use superb-ai/deta-swin-large with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("object-detection", model="superb-ai/deta-swin-large") # Load model directly
from transformers import AutoModelForObjectDetection
model = AutoModelForObjectDetection.from_pretrained("superb-ai/deta-swin-large", dtype="auto")By Jeffrey Ouyang-Zhang, Jang Hyun Cho, Xingyi Zhou, Philipp Krähenbühl
From the paper NMS Strikes Back.
TL; DR. Detection Transformers with Assignment (DETA) re-introduce IoU assignment and NMS for transformer-based detectors. DETA trains and tests comparibly as fast as Deformable-DETR and converges much faster (50.2 mAP in 12 epochs on COCO).