Hugging Face's logo

csgaobb
/
UniADet

Image Segmentation
PyTorch
English
anomaly-detection
zero-shot
few-shot
vision
clip
dinov2
dinov3
industrial-inspection
medical-imaging
Model card Files
xet
 Community
UniADet / README.md
csgaobb's picture
csgaobb
Upload UniADet MSDCS weights and model card
f427196 verified
preview code
|
Raw History Blame Contribute Delete
8.46 kB
metadata 
license: other
license_name: uniadet-weights
license_link: https://neurips.cc/virtual/2026/poster/149035
language:
  - en
pipeline_tag: image-segmentation
tags:
  - anomaly-detection
  - zero-shot
  - few-shot
  - vision
  - pytorch
  - clip
  - dinov2
  - dinov3
  - industrial-inspection
  - medical-imaging
gated: auto
extra_gated_heading: Request access to UniADet weights
extra_gated_description: >-
  Access is granted after you submit the form below. Please use an institutional
  email when possible.
extra_gated_button_content: Agree and request access
extra_gated_prompt: >
  UniADet MSDCS weights are released for research and evaluation. By requesting
  access you agree that: (1) you will cite the UniADet paper if you use these
  weights; (2) you will not redistribute the weights as a standalone package
  without this model card; (3) the authors may keep a record of this access
  request (Hugging Face username, name, affiliation, email, country, intended
  use, and request time) to measure academic and industrial adoption. This is an
  access-request log, not a per-file download log. Hugging Face also counts
  anonymous repository downloads automatically.
extra_gated_fields:
  Full name: text
  Affiliation: text
  Official email: text
  Position:
    type: select
    options:
      - Faculty
      - Researcher
      - PhD student
      - Master student
      - Undergraduate
      - Engineer
      - Other
  Country: country
  I want to use this model for:
    type: select
    options:
      - Academic research
      - Teaching
      - Industrial R&D
      - Benchmark reproduction
      - label: Other
        value: other
  Brief description of intended use: text
  I agree to cite UniADet and not redistribute the weights without this model card: checkbox

UniADet

Official MSDCS weights of One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection, NeurIPS 2026.

This Hugging Face repository stores learnable MSDCS checkpoints only. Training and evaluation code is in a separate GitHub repository: gaobb/UniADet. Frozen CLIP / DINOv2 / DINOv3 backbones are not included here.

NeurIPS GitHub HF downloads

News

  • [2026-11-09]: Pre-trained MSDCS weights are released in this repository (gated: request access, then hf download).
  • [2026-09-25]: UniADet has been accepted to NeurIPS 2026. Official page: Poster.

Introduction

UniADet is a language-free universal (zero- and few-shot) visual anomaly detection framework. It outperforms language-dependent zero-/few-shot AD models while remaining simple and efficient: only 0.015M or 0.020M learnable parameters on top of a frozen foundation model.

Language-dependent vs language-free anomaly detection
  • Language prompts and text encoders are unnecessary. The same recipe works with CLIP, DINOv2-Reg, and DINOv3.
  • Global anomaly classification and local anomaly segmentation are fully decoupled across multi-scale hierarchical features (MSDCS: layer-wise cls/seg weights).
  • Few-shot UniADet is the first to outperform full-shot state-of-the-art on several industrial benchmarks.
UniADet framework

Checkpoints in this repo

MSDCS uses 5 layers, dual cls/seg embeddings, and 2 tokens (normal / anomaly): (5 \times 2 \times 2 \times D). Files are fp32 .pth with a small pickle header. Each file stores {"msdcs": state_dict} only.

Backbone (D) Learnable params File size Frozen backbone (not in this repo)
CLIP ViT-L/14@336px 768 (1.5\times10^{-2}) M 64.5 KB 342.9 M
DINOv2-Reg ViT-L-14 1024 (2.0\times10^{-2}) M 84.5 KB 304.4 M
DINOv3 ViT-L-16 1024 (2.0\times10^{-2}) M 84.5 KB 303.2 M

Layout after download (same as $UNIADET_CKPT in the code repo):

train_on_<visa|mvtec>_zs_<backbone>_imagesize<H>_1015/epoch_15.pth
Path Backbone Trained on Input size
train_on_visa_zs_ViT-L-14@336px_imagesize518_1015/epoch_15.pth CLIP ViT-L/14@336px VisA 518
train_on_mvtec_zs_ViT-L-14@336px_imagesize518_1015/epoch_15.pth CLIP ViT-L/14@336px MVTec 518
train_on_visa_zs_ViT-L-14-DINOv2Reg_imagesize518_1015/epoch_15.pth DINOv2-Reg ViT-L/14 VisA 518
train_on_mvtec_zs_ViT-L-14-DINOv2Reg_imagesize518_1015/epoch_15.pth DINOv2-Reg ViT-L/14 MVTec 518
train_on_visa_zs_ViT-L-16-DINOv3_imagesize512_1015/epoch_15.pth DINOv3 ViT-L/16 VisA 512
train_on_mvtec_zs_ViT-L-16-DINOv3_imagesize512_1015/epoch_15.pth DINOv3 ViT-L/16 MVTec 512

Paper protocol: train on VisA, test on the target set, unless you specifically need the MVTec-trained weights.

How to download

This repo is gated. Open https://huggingface.co/csgaobb/UniADet while logged in, fill the form, then:

pip install -U huggingface_hub
hf auth login
hf download csgaobb/UniADet --local-dir "$UNIADET_CKPT"

Please use hf download / snapshot_download (whole repo). That fetches config.json, which is the file Hugging Face uses to count downloads. Directly clicking a single .pth in the file browser may not increment the public download counter.

from huggingface_hub import snapshot_download

snapshot_download(repo_id="csgaobb/UniADet", local_dir="checkpoints")

Then follow the GitHub docs: environment, data, training / evaluation.

Results (Image-AUROC / Pixel-AUPR)

Backbone Shot MVTec-AD VisA Real-IAD
CLIP (ViT-L/14@336px) 0 92.4 / 42.8 88.0 / 28.0 78.6 / 33.6
CLIP (ViT-L/14@336px) 4 97.7 / 58.8 93.3 / 36.7 84.3 / 37.2
DINOv2 (Register ViT-L/14) 0 93.5 / 50.9 91.3 / 32.7 82.5 / 43.1
DINOv2 (Register ViT-L/14) 4 98.7 / 65.4 96.9 / 45.2 90.3 / 48.5
DINOv3 (ViT-L/16) 0 94.0 / 52.7 91.9 / 32.5 81.2 / 41.6
DINOv3 (ViT-L/16) 4 98.2 / 69.0 97.1 / 45.5 88.5 / 49.8

Full comparisons, ablations, and efficiency tables: GitHub README.

Intended use

  • Intended: academic research and reproduction of UniADet zero-shot / few-shot visual anomaly detection on public industrial and medical benchmarks.
  • Out of scope: clinical diagnosis, safety-critical deployment without additional validation, or treating these tiny MSDCS files as a standalone detector without the frozen backbone and official code.

Bias, risks, limitations

  • Weights were trained on auxiliary industrial data (VisA or MVTec). Cross-domain performance depends on the frozen backbone and the evaluation protocol in the paper.
  • Checkpoints contain MSDCS embeddings only. You still need the corresponding official CLIP / DINOv2-Reg / DINOv3 weights.
  • Gated access records who requested the repo, not every subsequent GET of a weight file.

Citation

If you find this work useful in your research, please consider citing:

@inproceedings{uniadet,
  title={One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection},
  author={Gao, Bin-Bin},
  booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
  year={2026},
  url={https://neurips.cc/virtual/2026/poster/149035}
}