Unifying Multiple Foundation Models for Advanced Computational Pathology
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910020670586880 |
|---|---|
| author | Lei, Wenhui Tan, Yusheng Li, Anqi Chen, Hanyu Tian, Hengrui Li, Ruiying Jiang, Zhengqun Yan, Fang Zhang, Xiaofan Zhang, Shaoting |
| author_facet | Lei, Wenhui Tan, Yusheng Li, Anqi Chen, Hanyu Tian, Hengrui Li, Ruiying Jiang, Zhengqun Yan, Fang Zhang, Xiaofan Zhang, Shaoting |
| contents | Foundation models have substantially advanced computational pathology by learning transferable visual representations from large histological datasets, yet their performance varies widely across tasks due to differences in training data composition and reliance on proprietary datasets that cannot be cumulatively expanded. Existing efforts to combine foundation models through offline distillation partially mitigate this issue but require dedicated distillation data and repeated retraining to integrate new models. Here we present Shazam, an online integration model that adaptively combines multiple pretrained pathology foundation models within a unified and scalable representation learning paradigm. Our findings show that fusing multi-level features through adaptive expert weighting and online distillation enables efficient consolidation of complementary model strengths without additional pretraining. Across spatial transcriptomics prediction, survival prognosis, tile-level classification, and visual question answering, Shazam consistently outperforms strong individual models, demonstrating that online model integration provides a practical and extensible strategy for advancing computational pathology. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00736 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unifying Multiple Foundation Models for Advanced Computational Pathology Lei, Wenhui Tan, Yusheng Li, Anqi Chen, Hanyu Tian, Hengrui Li, Ruiying Jiang, Zhengqun Yan, Fang Zhang, Xiaofan Zhang, Shaoting Computer Vision and Pattern Recognition Foundation models have substantially advanced computational pathology by learning transferable visual representations from large histological datasets, yet their performance varies widely across tasks due to differences in training data composition and reliance on proprietary datasets that cannot be cumulatively expanded. Existing efforts to combine foundation models through offline distillation partially mitigate this issue but require dedicated distillation data and repeated retraining to integrate new models. Here we present Shazam, an online integration model that adaptively combines multiple pretrained pathology foundation models within a unified and scalable representation learning paradigm. Our findings show that fusing multi-level features through adaptive expert weighting and online distillation enables efficient consolidation of complementary model strengths without additional pretraining. Across spatial transcriptomics prediction, survival prognosis, tile-level classification, and visual question answering, Shazam consistently outperforms strong individual models, demonstrating that online model integration provides a practical and extensible strategy for advancing computational pathology. |
| title | Unifying Multiple Foundation Models for Advanced Computational Pathology |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.00736 |