# Prompt-MIL: Boosting Multi-Instance Learning Schemes via Task-specific Prompt Tuning

arXiv: https://arxiv.org/abs/2303.12214 · HTML: https://mlsanity.com/paper/2303.12214/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 21 Mar 2023.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning](https://mlsanity.com/paper/2206.02647/) (2022)
- [PPT: Pre-trained Prompt Tuning for Few-shot Learning](https://mlsanity.com/paper/2109.04332/) (2021)
- [Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification](https://mlsanity.com/paper/1504.07947/) (2015)
- [BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images](https://mlsanity.com/paper/2111.04740/) (2021)
- [Streaming convolutional neural networks for end-to-end learning with multi-megapixel images](https://mlsanity.com/paper/1911.04432/) (2019)
- [The Power of Prompt Tuning for Low-Resource Semantic Parsing](https://mlsanity.com/paper/2110.08525/) (2021)
- [Gigapixel Whole-Slide Images Classification using Locally Supervised Learning](https://mlsanity.com/paper/2207.08267/) (2022)
- [Multi-Stage Pathological Image Classification using Semantic Segmentation](https://mlsanity.com/paper/1910.04473/) (2019)

## Built on by (most cited first, 15 of 15)

- [A General-Purpose Self-Supervised Model for Computational Pathology](https://mlsanity.com/paper/2308.15474/) (2023)
- [2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification](https://mlsanity.com/paper/2412.00678/) (2024)
- [SAM-Path: A Segment Anything Model for Semantic Segmentation in Digital Pathology](https://mlsanity.com/paper/2307.09570/) (2023)
- [SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology](https://mlsanity.com/paper/2312.15010/) (2023)
- [PromptSmooth: Certifying Robustness of Medical Vision-Language Models via Prompt Learning](https://mlsanity.com/paper/2408.16769/) (2024)
- [BAPLe: Backdoor Attacks on Medical Foundational Models using Prompt Learning](https://mlsanity.com/paper/2408.07440/) (2024)
- [Benchmarking Embedding Aggregation Methods in Computational Pathology: A Clinical Data Perspective](https://mlsanity.com/paper/2407.07841/) (2024)
- [Recent Advances in Medical Imaging Segmentation: A Survey](https://mlsanity.com/paper/2505.09274/) (2025)
- [Fine-grained Prompt Tuning: A Parameter and Memory Efficient Transfer Learning Method for High-resolution Medical Image Classification](https://mlsanity.com/paper/2403.07576/) (2024)
- [Prompt-Guided Foundation Model Tuning for Pathology Image Classification](https://mlsanity.com/paper/2403.12537/) (2024)
- [Long-MIL: Scaling Long Contextual Multiple Instance Learning for Histopathology Whole Slide Image Analysis](https://mlsanity.com/paper/2311.12885/) (2023)
- [PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization](https://mlsanity.com/paper/2503.06482/) (2025)
- [Rethinking Pre-Trained Feature Extractor Selection in Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2408.01167/) (2024)
- [Cross-Patient Pseudo Bags Generation and Curriculum Contrastive Learning for Imbalanced Multiclassification of Whole Slide Image](https://mlsanity.com/paper/2411.11262/) (2024)
- [ReqBrain: Task-Specific Instruction Tuning of LLMs for AI-Assisted Requirements Generation](https://mlsanity.com/paper/2505.17632/) (2025)

## Abstract (arXiv)

Whole slide image (WSI) classification is a critical task in computational pathology, requiring the processing of gigapixel-sized images, which is challenging for current deep-learning methods. Current state of the art methods are based on multi-instance learning schemes (MIL), which usually rely on pretrained features to represent the instances. Due to the lack of task-specific annotated data, these features are either obtained from well-established backbones on natural images, or, more recently from self-supervised models pretrained on histopathology. However, both approaches yield task-agnostic features, resulting in performance loss compared to the appropriate task-related supervision, if available. In this paper, we show that when task-specific annotations are limited, we can inject such supervision into downstream task training, to reduce the gap between fully task-tuned and task agnostic features. We propose Prompt-MIL, an MIL framework that integrates prompts into WSI classification. Prompt-MIL adopts a prompt tuning mechanism, where only a small fraction of parameters calibrates the pretrained features to encode task-specific information, rather than the conventional full fine-tuning approaches. Extensive experiments on three WSI datasets, TCGA-BRCA, TCGA-CRC, and BRIGHT, demonstrate the superiority of Prompt-MIL over conventional MIL methods, achieving a relative improvement of 1.49%-4.03% in accuracy and 0.25%-8.97% in AUROC while using fewer than 0.3% additional parameters. Compared to conventional full fine-tuning approaches, we fine-tune less than 1.3% of the parameters, yet achieve a relative improvement of 1.29%-13.61% in accuracy and 3.22%-27.18% in AUROC and reduce GPU memory consumption by 38%-45% while training 21%-27% faster. Our code is available at https://github.com/cvlab-stonybrook/PromptMIL.