Viet-Anh on Software Logo

What is: RetinaNet-RS?

SourceSimple Training Strategies and Model Scaling for Object Detection
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

RetinaNet-RS is an object detection model produced through a model scaling method based on changing the the input resolution and ResNet backbone depth. For RetinaNet, we scale up input resolution from 512 to 768 and the ResNet backbone depth from 50 to 152. As RetinaNet performs dense one-stage object detection, the authors find scaling up input resolution leads to large resolution feature maps hence more anchors to process. This results in a higher capacity dense prediction heads and expensive NMS. Scaling stops at input resolution 768 × 768 for RetinaNet.