# zjhuang22/maskscoring_rcnn

Codes for paper "Mask Scoring R-CNN".

Repository: https://github.com/zjhuang22/maskscoring_rcnn
Canonical: https://ross.abutalabs.com/products/maskscoring_rcnn
Language: Python
License: MIT
License Family: permissive
Last push: 2020-11-06T08:07:33+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": 2744, "days_push": 2126, "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 1895, forks 372 (observed 2026-08-28T04:05:50.836488+00:00)

## What it is
Official PyTorch implementation of Mask Scoring R-CNN (CVPR 2019), built on maskrcnn-benchmark. It adds a network block that learns the quality of predicted instance masks by regressing mask IoU, improving instance segmentation accuracy on COCO.

## Use cases
- instance segmentation with mask quality scoring
- train Mask Scoring R-CNN on COCO
- improve mask AP over Mask R-CNN baseline
- reproduce CVPR 2019 paper results
- research on mask IoU prediction
- pretrained models for instance segmentation

## When to choose
- you need state-of-the-art instance segmentation with calibrated mask scores
- you want to reproduce or extend the MS R-CNN paper
- you need pretrained COCO instance segmentation models

## When to avoid
- you need a maintained, up-to-date framework (last release 2020, based on deprecated maskrcnn-benchmark)
- you want simple inference without training infrastructure
- you need Windows or CPU-only support

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: instance-segmentation, mask-scoring, mask-rcnn, cvpr-2019, pytorch, coco, research-code, linux, gpu

## Member repositories
- zjhuang22/maskscoring_rcnn (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:50.836488+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 2026-08-30T03:12:52.439399+00:00, confidence not recorded.
  - readme: https://github.com/zjhuang22/maskscoring_rcnn (fetched 2026-08-28T04:05:50.836488+00:00, sha f8f3c4c65ef8)
- Data as of 2026-08-30T08:39:29.467469+00:00.