# xingyizhou/ExtremeNet

Bottom-up Object Detection by Grouping Extreme and Center Points

Repository: https://github.com/xingyizhou/ExtremeNet
Canonical: https://ross.abutalabs.com/products/extremenet
Language: Python
License: BSD-3-Clause
License Family: permissive
Last push: 2019-04-19T02:32:30+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2796, "days_push": 2694, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1031, forks 172 (observed 2026-08-28T04:03:18.074762+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: object-detection, keypoint-estimation, pytorch, cvpr-2019, research-code, instance-segmentation, coco, linux, gpu

## Member repositories
- xingyizhou/ExtremeNet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:18.074762+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:07:30.519261+00:00, confidence not recorded.
  - readme: https://github.com/xingyizhou/ExtremeNet (fetched 2026-08-28T04:03:18.074762+00:00, sha 4e125f9a3da1)
- Data as of 2026-08-30T08:39:29.467469+00:00.