joe-siyuan-qiao/DetectoRS

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1147 stars · 174 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Official PyTorch implementation of DetectoRS, a state-of-the-art object detection and instance segmentation model using Recursive Feature Pyramid and Switchable Atrous Convolution, built on the MMDetection codebase. It provides configs and pretrained models achieving strong COCO benchmark results.

Use cases

• train a state-of-the-art object detection model on COCO
• run instance segmentation with pretrained DetectoRS checkpoints
• apply Recursive Feature Pyramid and Switchable Atrous Convolution to my detector
• reproduce DetectoRS paper results
• integrate RFP and SAC into mmdetection models

When to choose

• you need top-tier COCO detection/segmentation accuracy with pretrained models
• you already use MMDetection and want to add RFP/SAC components
• you are reproducing or extending the DetectoRS research

When to avoid

• you need a lightweight or real-time detector
• you want actively maintained code - it is frozen at PyTorch 1.4 and superseded by MMDetection support
• you work outside the MMDetection/PyTorch ecosystem

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning python object-detection instance-segmentation mmdetection pytorch research-code coco linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="joe-siyuan-qiao/DetectoRS")