MI-VisionShot: Few-shot adaptation of vision-language models for slide-level classification of histopathological images

Pablo Meseguer, Rocío del Amor, Valery Naranjo
10/21/2024
cs.CVcs.AI

Official code: cvblab/MIVisionShot (0 stars, last commit 2025-09-09).

Abstract

Vision-language supervision has made remarkable strides in learning visual representations from textual guidance. In digital pathology, vision-language models (VLM), pre-trained on curated datasets of histological image-captions, have been adapted to downstream tasks, such as region of interest classification. Zero-shot transfer for slide-level prediction has been formulated by MI-Zero, but it exhibits high variability depending on the textual prompts. Inspired by prototypical learning, we propose MI-VisionShot, a training-free adaptation method on top of VLMs to predict slide-level labels in few-shot learning scenarios. Our framework takes advantage of the excellent representation learning of VLM to create prototype-based classifiers under a multiple-instance setting by retrieving the most discriminative patches within each slide. Experimentation through different settings shows the ability of MI-VisionShot to surpass zero-shot transfer with lower variability, even in low-shot scenarios. Code coming soon at thttps://github.com/cvblab/MIVisionShot.

View on arXivView PDF

Code Implementations(1)

cvblab/MIVisionShotOfficial100%
00PythonMar 11, 20241 years ago

Similar Papers

Slide-Level Prompt Learning with Vision Language Models for Few-Shot Multiple Instance Learning in Histopathology

92% match1 repo42025

MGPATH: Vision-Language Model with Multi-Granular Prompt Learning for Few-Shot WSI Classification

90% match1 repo132025

Initialization matters in few-shot adaptation of vision-language models for histopathological image classification

90% match2026

Boosting Vision-Language Models for Histopathology Classification: Predict all at once

89% match1 repo182024

VLEER: Vision and Language Embeddings for Explainable Whole Slide Image Representation

87% match2025

GMAT: Grounded Multi-Agent Clinical Description Generation for Text Encoder in Vision-Language MIL for Whole Slide Image Classification

87% match2025

Cite this paper

@article{meseguer2024mivisionshot,
  title  = {MI-VisionShot: Few-shot adaptation of vision-language models for slide-level classification of histopathological images},
  author = {Pablo Meseguer and Rocío del Amor and Valery Naranjo},
  year   = {2024},
  eprint = {2410.15881},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.15881v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.15881.svg)](https://codeofpaper.com/paper/2410.15881)

Discussion