MedCAL-Bench: A Comprehensive Benchmark on Cold-Start Active Learning with Foundation Models for Medical Image Analysis

• URL: http://arxiv.org/abs/2508.03441v1
• Date: Tue, 05 Aug 2025 13:39:39 GMT
• Title: MedCAL-Bench: A Comprehensive Benchmark on Cold-Start Active Learning with Foundation Models for Medical Image Analysis
• Authors: Ning Zhu, Xiaochuan Ma, Shaoting Zhang, Guotai Wang,
• Abstract summary: Cold-Start Active Learning (CSAL) aims to select informative samples for annotation without prior knowledge.<n>Most existing CSAL methods rely on Self-Supervised Learning (SSL) on the target dataset for feature extraction.<n>We propose MedCAL-Bench, the first systematic FM-based CSAL benchmark for medical image analysis.
• Score: 15.350816812760314
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cold-Start Active Learning (CSAL) aims to select informative samples for annotation without prior knowledge, which is important for improving annotation efficiency and model performance under a limited annotation budget in medical image analysis. Most existing CSAL methods rely on Self-Supervised Learning (SSL) on the target dataset for feature extraction, which is inefficient and limited by insufficient feature representation. Recently, pre-trained Foundation Models (FMs) have shown powerful feature extraction ability with a potential for better CSAL. However, this paradigm has been rarely investigated, with a lack of benchmarks for comparison of FMs in CSAL tasks. To this end, we propose MedCAL-Bench, the first systematic FM-based CSAL benchmark for medical image analysis. We evaluate 14 FMs and 7 CSAL strategies across 7 datasets under different annotation budgets, covering classification and segmentation tasks from diverse medical modalities. It is also the first CSAL benchmark that evaluates both the feature extraction and sample selection stages. Our experimental results reveal that: 1) Most FMs are effective feature extractors for CSAL, with DINO family performing the best in segmentation; 2) The performance differences of these FMs are large in segmentation tasks, while small for classification; 3) Different sample selection strategies should be considered in CSAL on different datasets, with Active Learning by Processing Surprisal (ALPS) performing the best in segmentation while RepDiv leading for classification. The code is available at https://github.com/HiLab-git/MedCAL-Bench.

Related papers

• OpenPath: Open-Set Active Learning for Pathology Image Classification via Pre-trained Vision-Language Models [22.494367900953645]
  We propose OpenPath, a novel open-set active learning approach for pathological image classification.<n>OpenPath significantly enhances the model's performance due to its high purity of selected samples.
  arXiv  Detail & Related papers  (2025-06-18T09:47:45Z)
• Class Balance Matters to Active Class-Incremental Learning [61.11786214164405]
  We aim to start from a pool of large-scale unlabeled data and then annotate the most informative samples for incremental learning.<n>We propose Class-Balanced Selection (CBS) strategy to achieve both class balance and informativeness in chosen samples.<n>Our CBS can be plugged and played into those CIL methods which are based on pretrained models with prompts tunning technique.
  arXiv  Detail & Related papers  (2024-12-09T16:37:27Z)
• Zero-shot capability of SAM-family models for bone segmentation in CT scans [1.6018376109260821]
  We use non-iterative, optimal'' prompting strategies to test the zero-shot capability of SAM-family models for bone CT segmentation. Our results show that the best settings depend on the model type and size, dataset characteristics and objective to optimize.
  arXiv  Detail & Related papers  (2024-11-13T14:16:22Z)
• Rethinking Pre-Trained Feature Extractor Selection in Multiple Instance Learning for Whole Slide Image Classification [2.375943263571389]
  Multiple instance learning (MIL) has become a preferred method for gigapixel whole slide image (WSI) classification without requiring patch-level annotations.<n>This study systematically evaluating MIL feature extractors across three dimensions: pre-training dataset, backbone model, and pre-training method.
  arXiv  Detail & Related papers  (2024-08-02T10:34:23Z)
• LLM-Select: Feature Selection with Large Language Models [64.5099482021597]
  Large language models (LLMs) are capable of selecting the most predictive features, with performance rivaling the standard tools of data science.<n>Our findings suggest that LLMs may be useful not only for selecting the best features for training but also for deciding which features to collect in the first place.
  arXiv  Detail & Related papers  (2024-07-02T22:23:40Z)
• TAAL: Test-time Augmentation for Active Learning in Medical Image Segmentation [7.856339385917824]
  This paper proposes Test-time Augmentation for Active Learning (TAAL), a novel semi-supervised active learning approach for segmentation. Our results on a publicly-available dataset of cardiac images show that TAAL outperforms existing baseline methods in both fully-supervised and semi-supervised settings.
  arXiv  Detail & Related papers  (2023-01-16T22:19:41Z)
• CIM: Class-Irrelevant Mapping for Few-Shot Classification [58.02773394658623]
  Few-shot classification (FSC) is one of the most concerned hot issues in recent years. How to appraise the pre-trained FEM is the most crucial focus in the FSC community. We propose a simple, flexible method, dubbed as Class-Irrelevant Mapping (CIM)
  arXiv  Detail & Related papers  (2021-09-07T03:26:24Z)
• SSLM: Self-Supervised Learning for Medical Diagnosis from MR Video [19.5917119072985]
  In this paper, we propose a self-supervised learning approach to learn the spatial anatomical representations from magnetic resonance (MR) video clips. The proposed pretext model learns meaningful spatial context-invariant representations. Different experiments show that the features learnt by the pretext model provide explainable performance in the downstream task.
  arXiv  Detail & Related papers  (2021-04-21T12:01:49Z)
• Shared Space Transfer Learning for analyzing multi-site fMRI data [83.41324371491774]
  Multi-voxel pattern analysis (MVPA) learns predictive models from task-based functional magnetic resonance imaging (fMRI) data. MVPA works best with a well-designed feature set and an adequate sample size. Most fMRI datasets are noisy, high-dimensional, expensive to collect, and with small sample sizes. This paper proposes the Shared Space Transfer Learning (SSTL) as a novel transfer learning approach.
  arXiv  Detail & Related papers  (2020-10-24T08:50:26Z)
• Prior Guided Feature Enrichment Network for Few-Shot Segmentation [64.91560451900125]
  State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results. Few-shot segmentation is proposed to tackle this problem by learning a model that quickly adapts to new classes with a few labeled support samples. Theses frameworks still face the challenge of generalization ability reduction on unseen classes due to inappropriate use of high-level semantic information.
  arXiv  Detail & Related papers  (2020-08-04T10:41:32Z)
• Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
  We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training. We experimentally verify that the new dataset can significantly improve the ability of the learned FER model. To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
  arXiv  Detail & Related papers  (2020-05-18T09:36:51Z)

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.