# czczup/ViT-Adapter

[ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions

Repository: https://github.com/czczup/ViT-Adapter
Canonical: https://ross.abutalabs.com/products/vit-adapter
Homepage: https://arxiv.org/abs/2205.08534
Language: Python
License: NOASSERTION
License Family: other
Topics: adapter, object-detection, semantic-segmentation, vision-transformer
Last push: 2025-06-03T15:00:23+00:00

## Health v2 (maintenance only)
Score: 34/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 24, release rhythm 8, longevity 100
- inputs: {"age_days": 1570, "days_push": 456, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1503, forks 155 (observed 2026-08-28T04:04:54.663885+00:00)

## What it is
Official PyTorch implementation of ViT-Adapter, an ICLR 2023 Spotlight paper introducing a pre-training-free adapter that lets plain Vision Transformers achieve strong dense prediction performance. It provides models and configs for object detection, instance segmentation, and semantic segmentation built on MMDetection and MMSegmentation.

## Use cases
- run object detection with a plain ViT backbone on COCO
- perform semantic segmentation on ADE20K or Cityscapes with ViT-Adapter
- reproduce ICLR 2023 paper results for dense predictions
- fine-tune a plain ViT for instance and panoptic segmentation
- compare adapter-based ViT against vision-specific transformers
- use pretrained ViT-Adapter checkpoints in detection pipelines

## When to choose
- you need state-of-the-art dense prediction results with a plain ViT backbone
- you already use MMDetection or MMSegmentation ecosystems
- you want pretrained checkpoints for detection and segmentation research

## When to avoid
- you need a lightweight inference-only library without the OpenMMLab stack
- your project requires a permissive, clearly defined license
- you work outside PyTorch or lack GPU resources

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: vision-transformer, adapter, object-detection, semantic-segmentation, instance-segmentation, panoptic-segmentation, iclr-2023, mmdetection, dense-prediction, gpu

## Member repositories
- czczup/ViT-Adapter (main) score 34

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:54.663885+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 2026-08-30T04:32:48.103628+00:00, confidence not recorded.
  - readme: https://github.com/czczup/ViT-Adapter (fetched 2026-08-28T04:04:54.663885+00:00, sha 9e821373054e)
  - homepage: https://arxiv.org/abs/2205.08534 (fetched 2026-08-29T11:37:33.600337+00:00, sha 9df863f0976f)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T11:37:33.603120+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T11:37:33.606653+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T11:37:33.608496+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T11:37:33.604970+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.