ModelAufgelistetExtern

MoA Lee2025 WACV

This repository contains model checkpoints from an independent reproduction of:

Quellehuggingface.co/g1g122/MoA_Lee2025_WACV/tree/f605573bbbbaa9daeab26dcd8f04e5bdbdc3ea45

ArtOtherBasismodelllaion/CLIP-ViT-B-16-laion2B-s34B-b88KVersionArt paintingCBewertung

Modellquelle

Art: Other
Dateigröße: 345 MB
Basismodell: laion/CLIP-ViT-B-16-laion2B-s34B-b88K
Version: vArt painting
Aktualisiert: 10. Okt. 2026
Quelle: Hugging Face

Quellenbeschreibung

MoA Lee 2025 WACV — Independent Reproduction

This repository contains model checkpoints from an independent reproduction of:

Domain Generalization using Large Pretrained Models with Mixture-of-Adapters
Gyuseong Lee, Wooseok Jang, Jinhyeon Kim, Jaewoo Jung, and Seungryong Kim
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025

Paper: https://doi.org/10.1109/WACV61041.2025.00801

This repository is not affiliated with or maintained by the original authors.

Model description

The checkpoints use an OpenCLIP ViT-B/16 backbone pretrained on LAION-2B:

Base model: laion/CLIP-ViT-B-16-laion2B-s34B-b88K
Dataset: PACS
Task: Domain generalization
Framework: PyTorch

Four leave-one-domain-out checkpoints are provided. Each checkpoint corresponds to one held-out PACS target domain.

Checkpoints

Held-out target domain	Checkpoint
Art painting	`pacs/art_painting.pt`
Cartoon	`pacs/cartoon.pt`
Photo	`pacs/photo.pt`
Sketch	`pacs/sketch.pt`

Checkpoint format

Each .pt checkpoint contains:

model state
optimizer state
training step
evaluation metrics
model metadata

The checkpoints require the accompanying Engram MoA implementation for model construction and evaluation.

License and attribution

The independently implemented Engram MoA code and checkpoints are released under the MIT License.

The checkpoints are based on OpenCLIP ViT-B/16 pretrained weights. OpenCLIP and the corresponding base model remain subject to their original license and attribution requirements.

Citation

@inproceedings{DBLP:conf/wacv/LeeJKJK25,
  author       = {Gyuseong Lee and
                  Wooseok Jang and
                  Jinhyeon Kim and
                  Jaewoo Jung and
                  Seungryong Kim},
  title        = {Domain Generalization using Large Pretrained Models with Mixture-of-Adapters},
  booktitle    = {{IEEE/CVF} Winter Conference on Applications of Computer Vision, {WACV}
                  2025, Tucson, AZ, USA, February 26 - March 6, 2025},
  pages        = {8259--8269},
  publisher    = {{IEEE}},
  year         = {2025},
  url          = {https://doi.org/10.1109/WACV61041.2025.00801},
  doi          = {10.1109/WACV61041.2025.00801},
  timestamp    = {Wed, 23 Apr 2025 11:40:59 +0200},
  biburl       = {https://dblp.org/rec/conf/wacv/LeeJKJK25.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

Quellen

1 Quelle

Hugging FacePrimärVersion f605573bbbbaa9daeab26dcd8f04e5bdbdc3ea45

huggingface.co/g1g122/MoA_Lee2025_WACV/tree/f605573bbbbaa9daeab26dcd8f04e5bdbdc3ea45

Verifiziert 10. Okt.

Modellartefakte

4 Artefakte

pacs/art_painting.pt

pt · 345 MB · SHA-256 458602d720d2…ef0e · Hugging Face

Herunterladen

pacs/cartoon.pt

pt · 345 MB · SHA-256 2ee26bdbaa53…6928 · Hugging Face

Herunterladen

pacs/photo.pt

pt · 345 MB · SHA-256 23f2537dfd37…7522 · Hugging Face

Herunterladen

pacs/sketch.pt

pt · 345 MB · SHA-256 70ba7923c527…a6c0 · Hugging Face

Herunterladen

Quellenauszüge

2 Auszüge

Readme1. Aug.huggingface.co/g1g122/MoA_Lee2025_WACV

--- license: mit datasets: - flwrlabs/pacs metrics: - accuracy base_model: - laion/CLIP-ViT-B-16-laion2B-s34B-b88K pipeline_tag: image-classification tags: - domain-generalization - mixture-of-adapters - pytorch --- # MoA Lee 2025 WACV — Independent Reproduction This repository contains model checkpoints from an independent reproduction of: **Domain Generalization using Large Pretrained Models with Mixture-of-Adapters** Gyuseong Lee, Wooseok Jang, Jinhyeon Kim, Jaewoo Jung, and Seungryong Kim IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025 - Paper: https://doi.org/10.1109/WACV61041.2025.00801 This repository is not affiliated with or maintained by the original authors. ## Model description The checkpoints use an OpenCLIP ViT-B/16 backbone pretrained on LAION-2B: - Base model: [laion/CLIP-ViT-B-16-laion2B-s34B-b88K](https://huggingface.co/laion/CLIP-ViT-B-16-laion2B-s34B-b88K) - Dataset: PACS - Task: Domain generalization - Framework: PyTorch Four leave-one-domain-out checkpoints are provided. Each checkpoint corresponds to one held-out PACS target domain. ## Checkpoints | Held-out target domain | Checkpoint | |---|---| | Art painting | `pacs/art_painting.pt` | | Cartoon | `pacs/cartoon.pt` | | Photo | `pacs/photo.pt` | | Sketch | `pacs/sketch.pt` | ## Checkpoint format Each `.pt` checkpoint contains: - model state - optimizer state - training step - evaluation metrics - model metadata The checkpoints require the accompanying Engram MoA implementation for model construction and evaluation. ## License and attribution The independently implemented Engram MoA code and checkpoints are released under the MIT License. The checkpoints are based on OpenCLIP ViT-B/16 pretrained weights. OpenCLIP and the corresponding base model remain subject to their original license and attribution requirements. ## Citation ```bibtex @inproceedings{DBLP:conf/wacv/LeeJKJK25, author = {Gyuseong Lee and Wooseok Jang and Jinhyeon Kim and Jaewoo Jung and Seungryong Kim}, title = {Domain Generalization using Large Pretrained Models with Mixture-of-Adapters}, booktitle = {{IEEE/CVF} Winter Conference on Applications of Computer Vision, {WACV} 2025, Tucson, AZ, USA, February 26 - March 6, 2025}, pages = {8259--8269}, publisher = {{IEEE}}, year = {2025}, url = {https://doi.org/10.1109/WACV61041.2025.00801}, doi = {10.1109/WACV610...

Note1. Aug.huggingface.co/g1g122/MoA_Lee2025_WACV

Source context: 0 downloads · 0 likes · Pipeline image-classification · Repo g1g122/MoA_Lee2025_WACV