Project AURIONAI Use-Cases Research & Innovation
University of Gottingen
vision

CLIPSeg

Segmentation from text or image prompts on top of CLIP, from the paper "Image Segmentation Using Text and Image Prompts".

University of GottingenUniversity of GottingenGermany
Figure from the CLIPSeg paper: Architecture of CLIPSeg: We extend a frozen CLIP model (red and blue) with a transformer that segments the query image based on either a support image or a support prompt.
Levelmodel
Classvision
Parameters150.75M
Contextnot in the notes
Released18 Dec 2021
Opennessopen weights permissive
Runs onnot in the notes
Statusactive

R&D Topics

Open-vocabulary object detection and groundingproduced by

Identity

Developer
University of Gottingen
Family
not in the notes
Released
18 Dec 2021 sourcesannouncement page
Weights published
1 Nov 2022
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
Total parameters
150.75M sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
image
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 weights permissive
Licence
Apache License 2.0 sources
Access routes
open weights download, cloud marketplace
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
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/2112.10003 https://arxiv.org/abs/2112.10003
  2. huggingface.co/CIDAS/clipseg-rd64-refined https://huggingface.co/CIDAS/clipseg-rd64-refined
  3. ai.azure.com/catalog/models?task=image-segmentation https://ai.azure.com/catalog/models?task=image-segmentation
  4. huggingface.co/api/models?pipeline_tag=image-segmentation&so... https://huggingface.co/api/models?pipeline_tag=image-segmentation&sort=downloads&limit=50
  5. arxiv.org/html/2112.10003 https://arxiv.org/html/2112.10003

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