Project AURIONAI Use-Cases Research & Innovation
Amazon
visionfamily

WinCLIP

Zero-shot and few-shot anomaly classification and segmentation using CLIP. Paper by Jeong et al. (2023).

Figure from the WinCLIP paper: Language guided zero-/one-shot11 1 few-shot and few-normal-shot are used interchangeably in our case.anomaly segmentation from WinCLIP/WinCLIP+.
Levelfamily
Classvision
Parametersnot in the notes
Contextnot in the notes
Released26 Mar 2023
Opennessopen source
Runs onnot in the notes
Statusactive

R&D Topics

Identity

Developer
Amazon, KAIST
Family
not in the notes
Released
26 Mar 2023 sourcesannouncement page
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
dense transformer Window-based CLIP features compared with text prompts
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
image, text
Output
image
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open source
Licence
Apache License 2.0 sources
Access routes
not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
Licence is that of the Anomalib implementation (Apache-2.0).
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2303.14814 https://arxiv.org/abs/2303.14814
  2. github.com/open-edge-platform/anomalib https://github.com/open-edge-platform/anomalib
  3. anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/im... https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/index.html
  4. arxiv.org/html/2303.14814 https://arxiv.org/html/2303.14814

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "WinCLIP", https://aurion.semai.id/models/winclip/, records of October 2026.