# xuebinqin/DIS

This is the repo for our new project Highly Accurate Dichotomous Image Segmentation

Repository: https://github.com/xuebinqin/DIS
Canonical: https://ross.abutalabs.com/products/dis
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: background-removal, deep-learning, dichotomous-image-segmentation, computer-vision, u-2-net
Last push: 2024-09-23T06:27:07+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": 1640, "days_push": 709, "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 2568, forks 289 (observed 2026-08-28T04:07:01.248785+00:00)

## What it is
Official repository for the ECCV 2022 paper 'Highly Accurate Dichotomous Image Segmentation' (DIS), providing the DIS dataset, IS-Net model code, and pretrained weights like isnet-general-use.pth. It focuses on highly accurate segmentation of highly detailed objects, commonly used for background removal.

## Use cases
- remove background from images with deep learning
- segment highly detailed objects accurately
- download pretrained IS-Net model weights
- run inference on custom images with isnet-general-use
- train dichotomous image segmentation models
- try a hosted demo for background removal

## When to choose
- you need state-of-the-art high-resolution object segmentation or background removal
- you want the official DIS dataset and IS-Net reference implementation
- you are doing research on dichotomous image segmentation

## When to avoid
- you need the unreleased DIS V2.0 dataset and model
- you want a production-ready background removal service rather than research code
- you need segmentation of categories underrepresented in DIS V1.0 like animals or humans

## Facets
- artifact type: dataset
- maturity: maintenance
- function: image-processing, computer-vision, deep-learning, machine-learning
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python, cross-platform
- tags: image-segmentation, background-removal, dichotomous-image-segmentation, u2net, isnet, eccv-2022, salient-object-detection, model-weights

## Member repositories
- xuebinqin/DIS (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:01.248785+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 2026-08-30T02:23:22.562290+00:00, confidence not recorded.
  - readme: https://github.com/xuebinqin/DIS (fetched 2026-08-28T04:07:01.248785+00:00, sha 3a12e9e5b57f)
- Data as of 2026-08-30T08:39:29.467469+00:00.