aim-uofa/AdelaiDet

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

3478 stars · 654 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

AdelaiDet is an open-source Python toolbox built on Detectron2 that implements multiple instance-level detection and recognition algorithms such as FCOS, BlendMask, SOLOv2, CondInst, BoxInst, and ABCNet for text spotting. It ships pretrained model zoos, configs, training tools, and demos for object detection, instance segmentation, and scene text recognition.

Use cases

• train object detection models like FCOS on COCO
• run instance segmentation with BlendMask or SOLOv2
• detect and recognize scene text in images with ABCNet
• train weakly supervised segmentation with BoxInst from box annotations
• deploy pretrained detection models with ONNX export
• benchmark anchor-free detection baselines

When to choose

• you already use Detectron2 and want state-of-the-art instance-level detection algorithms
• you need research implementations of FCOS, BlendMask, SOLO, CondInst, or ABCNet with pretrained weights
• you need scene text detection and recognition in one toolbox

When to avoid

• you need a lightweight production inference server without Detectron2 dependencies
• you want actively developed features - the project is largely in maintenance mode
• you work outside PyTorch/CUDA environments

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing ocr computer-vision machine-learning deep-learning image-processing python object-detection instance-segmentation text-detection text-recognition detectron2 fcos blendmask abcnet solo boxinst condinst model-zoo linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="aim-uofa/AdelaiDet")