# Prompt-MIL: Boosting Multi-Instance Learning Schemes via Task-specific Prompt Tuning Source: [Prompt-MIL: Boosting Multi-Instance Learning Schemes via Task-specific Prompt Tuning]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:28:58.758Z Authors: Jingwei Zhang, Saarthak Kapse, Ke Ma, Prateek Prasanna, Joel Saltz, Maria Vakalopoulou, Dimitris Samaras Published: 2023-03-21T22:24:27.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on TCGA-BRCA (test)](): Image Classification; TCGA-BRCA (test); Accuracy: 93.47. - [Image Classification on TCGA-CRC (test)](): Image Classification; TCGA-CRC (test); Accuracy: 75.47. - [Image Classification on BRIGHT (test)](): Image Classification; BRIGHT (test); Accuracy: 0.6458. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()