# qqlu/Entity

EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation

Repository: https://github.com/qqlu/Entity
Canonical: https://ross.abutalabs.com/products/entity
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: image-segmentation, segmentation, pytorch, instance-segmentation, panoptic-segmentation, semantic-segmentation, object-detection, fcos, condinst, detectron2, pretrained-weights, pretrained-models, computer-vision, deep-learning, cnn, pretraining
Last push: 2023-11-30T05:28:46+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1866, "days_push": 1007, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1048, forks 61 (observed 2026-08-28T04:03:22.535097+00:00)

## What it is
EntitySeg is an open-source PyTorch toolbox for open-world, high-quality image segmentation, built on Detectron2. It aggregates multiple research implementations including entity segmentation, ultra-high-resolution image segmentation, and semi-supervised detection/segmentation.

## Use cases
- segment entities in images without predefined categories
- segment ultra high-resolution images with high quality
- run class-agnostic semi-supervised detection and segmentation
- evaluate open-vocabulary segmentation metrics
- fine-tune pretrained segmentation models on custom data

## When to choose
- you need state-of-the-art open-world or high-quality entity segmentation models
- you want research-grade implementations of CVPR/ICCV/NeurIPS segmentation papers
- you already use Detectron2 and want segmentation extensions with pretrained weights

## When to avoid
- you need a production-ready segmentation service with an API
- you need a simple out-of-the-box segmentation tool without deep learning setup
- you require a permissive open-source license (license is non-standard)

## Facets
- artifact type: library
- maturity: active
- function: image-processing, computer-vision, machine-learning, deep-learning
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python
- tags: image-segmentation, panoptic-segmentation, instance-segmentation, semantic-segmentation, detectron2, pytorch, open-world-segmentation, research-toolbox, pretrained-models, gpu, linux

## Member repositories
- qqlu/Entity (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:22.535097+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 2026-08-30T07:00:48.968104+00:00, confidence not recorded.
  - readme: https://github.com/qqlu/Entity (fetched 2026-08-28T04:03:22.535097+00:00, sha 9944be4b1df7)
- Data as of 2026-08-30T08:39:29.467469+00:00.