calls CenterMask “Anchor-free real-time instance segmentation; choose for faster inference than Mask R-CNN, but requires PyTorch.”
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
CenterMask is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named CenterMask among their alternatives. The relationship is not symmetric — how CenterMask rates them is a separate judgement, made when CenterMask is analysed in its own right.
calls CenterMask “Anchor-free real-time instance segmentation; choose for faster inference than Mask R-CNN, but requires PyTorch.”
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
calls CenterMask “Old anchor-free instance segmentation model implementation — choose only for that model.”
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
calls CenterMask “choose it if you specifically need the 2020 original CenterMask implementation for real-time anchor-free instance segmentation.”
RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]
calls CenterMask “Choose for an older anchor-free real-time instance segmentation model if you need a legacy baseline.”
SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.