xingyizhou/ExtremeNet

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1031 stars · 172 forks observed · 2026-08-28

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

Official PyTorch implementation of ExtremeNet, a CVPR 2019 bottom-up object detection method that detects four extreme points and one center point of objects via keypoint estimation and groups them into bounding boxes. It also supports coarse octagonal mask prediction and extreme-point-guided instance segmentation with DEXTR.

Use cases

• detect objects in images without region proposal networks
• reproduce CVPR 2019 bottom-up object detection results on COCO
• estimate object extreme points for coarse segmentation masks
• run a pretrained object detection model on custom images
• compare keypoint-based detection against anchor-based detectors
• implement extreme-point-guided instance segmentation

When to choose

• you need a research-grade bottom-up object detector with pretrained COCO weights
• you want extreme point predictions for segmentation-guided pipelines
• you are studying or extending keypoint-based detection methods

When to avoid

• you need a production-ready, actively maintained detection framework
• you require the latest architectures or modern PyTorch versions
• you want a simple out-of-the-box detection API without compiling custom NMS ops

Facets

library · maturity maintenance

machine-learning computer-vision image-processing computer-vision deep-learning machine-learning python object-detection keypoint-estimation pytorch cvpr-2019 research-code instance-segmentation coco linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="xingyizhou/ExtremeNet")