torchmil: A PyTorch-based library for deep Multiple Instance Learning
This work addresses a practical problem for researchers and practitioners in weakly supervised learning by offering a tool to accelerate progress and lower entry barriers, though it is incremental as it builds on existing MIL methods.
The authors tackled the lack of standardized tools for deep Multiple Instance Learning (MIL) by developing torchmil, an open-source PyTorch-based library that provides a unified framework, benchmark datasets, and comprehensive documentation, resulting in improved reproducibility and accessibility for the field.
Multiple Instance Learning (MIL) is a powerful framework for weakly supervised learning, particularly useful when fine-grained annotations are unavailable. Despite growing interest in deep MIL methods, the field lacks standardized tools for model development, evaluation, and comparison, which hinders reproducibility and accessibility. To address this, we present torchmil, an open-source Python library built on PyTorch. torchmil offers a unified, modular, and extensible framework, featuring basic building blocks for MIL models, a standardized data format, and a curated collection of benchmark datasets and models. The library includes comprehensive documentation and tutorials to support both practitioners and researchers. torchmil aims to accelerate progress in MIL and lower the entry barrier for new users. Available at https://torchmil.readthedocs.io.