{"ID":2849541,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.23145","arxiv_id":"2510.23145","title":"Implicit Modeling for Transferability Estimation of Vision Foundation Models","abstract":"Transferability estimation identifies the best pre-trained models for downstream tasks without incurring the high computational cost of full fine-tuning. This capability facilitates deployment and advances the pre-training and fine-tuning paradigm. However, existing methods often struggle to accurately assess transferability for emerging pre-trained models with diverse architectures, training strategies, and task alignments. In this work, we propose Implicit Transferability Modeling (ITM), a novel framework that implicitly models each model's intrinsic transferability, coupled with a Divide-and-Conquer Variational Approximation (DVA) strategy to efficiently approximate embedding space evolution. This design enables generalization across a broader range of models and downstream tasks. Extensive experiments on a comprehensive benchmark--spanning extensive training regimes and a wider variety of model types--demonstrate that ITM consistently outperforms existing methods in terms of stability, effectiveness, and efficiency.","short_abstract":"Transferability estimation identifies the best pre-trained models for downstream tasks without incurring the high computational cost of full fine-tuning. This capability facilitates deployment and advances the pre-training and fine-tuning paradigm. However, existing methods often struggle to accurately assess transfera...","url_abs":"https://arxiv.org/abs/2510.23145","url_pdf":"https://arxiv.org/pdf/2510.23145v1","authors":"[\"Yaoyan Zheng\",\"Huiqun Wang\",\"Nan Zhou\",\"Di Huang\"]","published":"2025-10-27T09:21:19Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}