Understanding the Transfer Limits of Vision Foundation Models

• URL: http://arxiv.org/abs/2601.15888v1
• Date: Thu, 22 Jan 2026 12:07:56 GMT
• Title: Understanding the Transfer Limits of Vision Foundation Models
• Authors: Shiqi Huang, Yipei Wang, Natasha Thorley, Alexander Ng, Shaheer Saeed, Mark Emberton, Shonit Punwani, Veeru Kasivisvanathan, Dean Barratt, Daniel Alexander, Yipeng Hu,
• Abstract summary: Foundation models leverage large-scale pretraining to capture extensive knowledge, demonstrating generalization in a wide range of language tasks.<n>We postulate that this limitation arises from a mismatch between pretraining objectives and the demands of downstream vision-and-imaging tasks.<n>Pretraining strategies like masked image reconstruction or contrastive learning shape representations for tasks such as recovery of generic visual patterns or global semantic structures.<n>Our findings indicate that better alignment between pretraining and downstream tasks, measured by simple divergence metrics such as maximum-mean-discrepancy (MMD) between the same features before and after fine-tuning, correlates with greater performance improvements and
• Score: 38.99867932557529
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Foundation models leverage large-scale pretraining to capture extensive knowledge, demonstrating generalization in a wide range of language tasks. By comparison, vision foundation models (VFMs) often exhibit uneven improvements across downstream tasks, despite substantial computational investment. We postulate that this limitation arises from a mismatch between pretraining objectives and the demands of downstream vision-and-imaging tasks. Pretraining strategies like masked image reconstruction or contrastive learning shape representations for tasks such as recovery of generic visual patterns or global semantic structures, which may not align with the task-specific requirements of downstream applications including segmentation, classification, or image synthesis. To investigate this in a concrete real-world clinical area, we assess two VFMs, a reconstruction-focused MAE-based model (ProFound) and a contrastive-learning-based model (ProViCNet), on five prostate multiparametric MR imaging tasks, examining how such task alignment influences transfer performance, i.e., from pretraining to fine-tuning. Our findings indicate that better alignment between pretraining and downstream tasks, measured by simple divergence metrics such as maximum-mean-discrepancy (MMD) between the same features before and after fine-tuning, correlates with greater performance improvements and faster convergence, emphasizing the importance of designing and analyzing pretraining objectives with downstream applicability in mind.

Related papers

• Compression then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding [53.18433310890516]
  Vision-language models advance multimodal representation learning by acquiring transferable semantic embeddings.<n>We propose CoMa, a compressed pre-training phase, which serves as a warm-up stage for contrastive learning.
  arXiv  Detail & Related papers  (2025-11-11T17:23:02Z)
• Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate [118.37653302885607]
  We present the Modality Integration Rate (MIR), an effective, robust, and generalized metric to indicate the multi-modal pre-training quality of Large Vision Language Models (LVLMs) MIR is indicative about training data selection, training strategy schedule, and model architecture design to get better pre-training results.
  arXiv  Detail & Related papers  (2024-10-09T17:59:04Z)
• How Effective is Pre-training of Large Masked Autoencoders for Downstream Earth Observation Tasks? [9.515532265294187]
  Self-supervised pre-training has proven highly effective for many computer vision tasks. It remains unclear under which conditions pre-trained models offer significant advantages over training from scratch.
  arXiv  Detail & Related papers  (2024-09-27T08:15:14Z)
• SG-MIM: Structured Knowledge Guided Efficient Pre-training for Dense Prediction [17.44991827937427]
  Masked Image Modeling techniques have redefined the landscape of computer vision. Despite their success, the full potential of MIM-based methods in dense prediction tasks, particularly in depth estimation, remains untapped. We propose SG-MIM, a novel Structured knowledge Guided Masked Image Modeling framework designed to enhance dense prediction tasks by utilizing structured knowledge alongside images.
  arXiv  Detail & Related papers  (2024-09-04T08:24:53Z)
• MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining [73.81862342673894]
  Foundation models have reshaped the landscape of Remote Sensing (RS) by enhancing various image interpretation tasks. transferring the pretrained models to downstream tasks may encounter task discrepancy due to their formulation of pretraining as image classification or object discrimination tasks. We conduct multi-task supervised pretraining on the SAMRS dataset, encompassing semantic segmentation, instance segmentation, and rotated object detection. Our models are finetuned on various RS downstream tasks, such as scene classification, horizontal and rotated object detection, semantic segmentation, and change detection.
  arXiv  Detail & Related papers  (2024-03-20T09:17:22Z)
• MIMIC: Mask Image Pre-training with Mix Contrastive Fine-tuning for Facial Expression Recognition [11.820043444385432]
  We introduce a novel FER training paradigm named Mask Image pre-training with MIx Contrastive fine-tuning (MIMIC) In the initial phase, we pre-train the ViT via masked image reconstruction on general images. In the fine-tuning stage, we introduce a mix-supervised contrastive learning process, which enhances the model with a more extensive range of positive samples.
  arXiv  Detail & Related papers  (2024-01-14T10:30:32Z)
• Self-Supervised Learning via Maximum Entropy Coding [57.56570417545023]
  We propose Maximum Entropy Coding (MEC) as a principled objective that explicitly optimize on the structure of the representation. MEC learns a more generalizable representation than previous methods based on specific pretext tasks. It achieves state-of-the-art performance consistently on various downstream tasks, including not only ImageNet linear probe, but also semi-supervised classification, object detection, instance segmentation, and object tracking.
  arXiv  Detail & Related papers  (2022-10-20T17:58:30Z)
• Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving [103.745551954983]
  In this paper, we investigate the transfer performance of various types of self-supervised methods, including MoCo and SimCLR, on three downstream tasks. We find that their performances are sub-optimal or even lag far behind the single-task baseline. We propose a simple yet effective pretrain-adapt-finetune paradigm for general multi-task training.
  arXiv  Detail & Related papers  (2022-09-19T12:15:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.