Ade20k Semantic Pmt Large 512 Dinov3

--- library_name: transformers license: mit tags: - vision - image-segmentation - semantic-segmentation - pytorch pipeline_tag: image-segmentation datasets: - ade20k base_model: - tue-mps/ade20k_semantic_pmt_large_512_dinov3 --- # PMT-DINOv3 (Large, 512px) for ADE20K Semantic Segmentation <div class="flex flex-wrap space-x-1"> <img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-DE3412?style=flat&logo=pytorch&logoColor=white"> <img alt="Transformers" src="https://img.shields.io/badge/Transformers-yellow?style=flat&logo=huggingface&logoColor=white"> </div> ## Overview This is the **large** variant of the PMT-DINOv3 model trained for **semantic segmentation** on ADE20K at **512x512** resolution. ## Model Details | Property | Value | |----------|-------| | Backbone | DINOv3 ViT-L/16 | | Input Resolution | 512x512 | | Task | Semantic Segmentation | | Dataset | ADE20K | ## Citation ```bibtex @inproceedings{cavagnero2026pmt, author = {Cavagnero, Niccolò and Norouzi, Narges and Dubbelman, Gijs and de Geus, Daan}, title = {PMT: Plain Mask Transformer for Image and Video Segmentation with Frozen Vision Encoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)}, year = {2026}, } ``` ## Acknowledgements - Original implementation: [tue-mps/pmt](https://github.com/tue-mps/pmt) - Paper: [arXiv:2503.19108](https://arxiv.org/abs/2603.25398)