We propose the development of a high-efficiency foundation model tailored for the MedMNIST v2 benchmark, utilizing a novel architecture based on Multi-Resolution Tree-Structured Vector Quantization (TSVQ). While current foundation models often rely on computationally expensive transformers, our approach focuses on a hierarchical quantization strategy. By employing multi-resolution codebooks, we can effectively capture and represent both long-range structural dependencies and intricate, short-range local correlations inherent in diverse medical imaging modalities, from pathology slides to radiological scans.
The core innovation lies in the tree-structured organization of the latent space. Unlike flat codebooks used in traditional VQ-VAEs, TSVQ offers a logarithmic search complexity, significantly reducing the energy required for both training and inference. This alignment with “Green Learning” principles ensures that our model achieves state-of-the-art representation fidelity without the massive carbon footprint typically associated with large-scale AI. By optimizing the codebook search and minimizing redundant parameters, we aim to demonstrate that high-performance medical AI can be both sustainable and accessible on modest hardware.
This framework serves as a robust, domain-agnostic foundation. The learned representations are designed to be highly transferable, enabling the model to excel across a spectrum of downstream tasks. Crucially, this architecture addresses the “small data” problem in clinical medicine; by pre-training on the comprehensive MedMNIST suite, the model can be fine-tuned on smaller, domain-specific clinical datasets with superior accuracy and stability. Ultimately, we aim to expand this green learning paradigm to broader healthcare applications, empowering the medical community with scalable, low-power, and high-precision diagnostic tools.
