GKD
> [!Note] > This repository contains model weights after domain-general distillation and task learning.
Source du modèle
- Type
- Other
- Taille du fichier
- 332 MB–2,47 GB
- Modèle de base
- facebook/deit-base-patch16-224
- Version
- vRevision 38a1b6e
- Mis à jour
- 27 sept. 2026
- Téléchargements
- 0
- Tâches
- Segmentation d'image
- Source
- Hugging Face
Extrait de la source
[!Note] > This repository contains model weights after domain-general distillation and task learning.
Sources
1 source
Sources
1 sourceVérifié 27 sept.
Artefacts du modèle
20 artefacts
Artefacts du modèle
20 artefactsGeneral_distillation/DINOv2_base2small_training_deit_IMNET_QSD_epoch100_citys_epoch300_512/checkpoint_300.pth
pth · 686 MB · SHA-256 2363d5ab5907…58f2 · Hugging Face
TéléchargerGeneral_distillation/DINOv2_base2small_training_deit_IMNET_QSD_epoch100_GTA_epoch300_512/checkpoint_300.pth
pth · 686 MB · SHA-256 ae27464e9359…f6ab · Hugging Face
TéléchargerGeneral_distillation/DINOv2_base2small_training_deit_IMNET_QSD_epoch100_potsdamRGB_epoch300_512/checkpoint_300.pth
pth · 686 MB · SHA-256 8ba941dda69d…22c0 · Hugging Face
TéléchargerGeneral_distillation/DINOv2_base2small_training_dino_IMNET_QSD_epoch100_citys_epoch300_512/checkpoint_300.pth
pth · 686 MB · SHA-256 aec7c0224663…8fb9 · Hugging Face
TéléchargerGeneral_distillation/DINOv2_base2small_training_dino_IMNET_QSD_epoch100_GTA_epoch300_512/checkpoint_300.pth
pth · 686 MB · SHA-256 4d5d09d43aa6…bd4b · Hugging Face
TéléchargerGeneral_distillation/DINOv2_base2small_training_dino_IMNET_QSD_epoch100_potsdamRGB_epoch300_512/checkpoint_300.pth
pth · 686 MB · SHA-256 5bbb3b8703fd…9f92 · Hugging Face
TéléchargerGeneral_distillation/DINOv2_large2base_training_deit_IMNET_QSD_epoch100_citys_epoch300_512/checkpoint_300.pth
pth · 2,47 GB · SHA-256 5bc2043bb1a7…c0b2 · Hugging Face
TéléchargerGeneral_distillation/DINOv2_large2base_training_deit_IMNET_QSD_epoch100_GTA_epoch300_512/checkpoint_300.pth
pth · 2,47 GB · SHA-256 c2f5e144cad6…142a · Hugging Face
TéléchargerGeneral_distillation/DINOv2_large2base_training_deit_IMNET_QSD_epoch100_potsdamRGB_epoch300_512/checkpoint_300.pth
pth · 2,47 GB · SHA-256 8b7765d89f72…bb51 · Hugging Face
TéléchargerGeneral_distillation/DINOv2_large2base_training_dino_IMNET_QSD_epoch100_citys_epoch300_512/checkpoint_300.pth
pth · 2,47 GB · SHA-256 72018a458959…7513 · Hugging Face
TéléchargerGeneral_distillation/DINOv2_large2base_training_dino_IMNET_QSD_epoch100_GTA_epoch300_512/checkpoint_300.pth
pth · 2,47 GB · SHA-256 7915aa930c2f…5518 · Hugging Face
TéléchargerGeneral_distillation/DINOv2_large2base_training_dino_IMNET_QSD_epoch100_potsdamRGB_epoch300_512/checkpoint_300.pth
pth · 2,47 GB · SHA-256 a054bbed9bc5…1220 · Hugging Face
TéléchargerTask_learning/DINOv2_base2small_training_deit_IMNET_QSD_epoch100_citys_epoch300_512_mask2former-40k_dg_citys-512x512.pth
pth · 332 MB · SHA-256 7020b6273349…08b5 · Hugging Face
TéléchargerTask_learning/DINOv2_base2small_training_deit_IMNET_QSD_epoch100_GTA_epoch300_512_mask2former-40k_dg_gta5-512x512.pth
pth · 338 MB · SHA-256 590db14f31a8…7ab9 · Hugging Face
TéléchargerTask_learning/DINOv2_base2small_training_dino_IMNET_QSD_epoch100_citys_epoch300_512_mask2former-40k_dg_citys-512x512.pth
pth · 337 MB · SHA-256 93c405655b51…73e7 · Hugging Face
TéléchargerTask_learning/DINOv2_base2small_training_dino_IMNET_QSD_epoch100_GTA_epoch300_512_mask2former-40k_dg_gta5-512x512.pth
pth · 333 MB · SHA-256 41bb404c54b0…573d · Hugging Face
TéléchargerTask_learning/DINOv2_large2base_training_deit_IMNET_QSD_epoch100_citys_epoch300_512_mask2former-40k_dg_citys-512x512.pth
pth · 588 MB · SHA-256 8bc84f83e507…91ff · Hugging Face
TéléchargerTask_learning/DINOv2_large2base_training_deit_IMNET_QSD_epoch100_GTA_epoch300_512_mask2former-40k_dg_gta5-512x512.pth
pth · 586 MB · SHA-256 5cd2e2829c7d…658c · Hugging Face
TéléchargerTask_learning/DINOv2_large2base_training_dino_IMNET_QSD_epoch100_citys_epoch300_512_mask2former-40k_dg_citys-512x512.pth
pth · 578 MB · SHA-256 e8acc1b55ff9…8bd1 · Hugging Face
TéléchargerTask_learning/DINOv2_large2base_training_dino_IMNET_QSD_epoch100_GTA_epoch300_512_mask2former-40k_dg_gta5-512x512.pth
pth · 588 MB · SHA-256 bebd369b8fbc…c3bf · Hugging Face
TéléchargerExtraits de sources
2 extraits
Extraits de sources
2 extraits--- library_name: transformers license: apache-2.0 base_model: - facebook/deit-base-patch16-224 - facebook/deit-small-patch16-224 pipeline_tag: image-segmentation --- <div align="center"> <img src="fig/logo.png" width="400px" height="400px"> </div> # [CVPR2026] Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation [](https://arxiv.org/pdf/2603.02554) > [!Note] > This repository contains model weights after domain-general distillation and task learning. ## Overview - `Motivation`: Conventional knowledge distillation approaches primarily preserve in-domain accuracy while neglecting out-of-domain generalization, which is essential under distribution shifts. This limitation becomes more severe with the emergence of vision foundation models (VFMs): although VFMs exhibit strong robustness on unseen data, distilling them with conventional KD often compromises this ability. - `Methodology`: GKD decouples representation learning from task learning. In the first stage, the student acquires domain-agnostic representations through selective feature distillation, and in the second stage, these representations are frozen for task adaptation, thereby mitigating overfitting to visible domains. To further support transfer, we introduce a query-based soft distillation mechanism, where student features act as queries to teacher representations to selectively retrieve transferable spatial knowledge from VFMs. Extensive experiments on five domain generalization benchmarks demonstrate that GKD consistently outperforms existing KD methods, achieving average gains of +1.9% in foundation-to-foundation (F2F) and +10.6% in foundation-to-local (F2L) distillation. <div align="center"> <img src="fig/GKD_Fig2.png" width="100%" height="100%"> </div> ### Comparison with State-of-the-Art KD <div align="center"> <img src="fig/table_1.png" width="" height=""> </div> ### Comparison with State-of-the-Art Domain Generalization (DG) <div align="center"> <img src="fig/table_2.png" width="80%" height="80%"> </div> ---
Source context: 0 downloads · 0 likes · Pipeline image-segmentation · Library transformers · Repo yongers/GKD
