Research
A Shared-Backbone Approach for Multi-Task MedMNIST Classification
arXiv:2609.06838v1 Announce Type: new Abstract: Multi-task biomedical classification requires models to generalize across disparate modalities and class distributions. We study 11 heterogeneous MedMNI
arXiv:2609.06838v1 Announce Type: new Abstract: Multi-task biomedical classification requires models to generalize across disparate modalities and class distributions. We study 11 heterogeneous MedMNIST datasets using the harmonic mean of per-task macro-F1. We evaluate three backbones with task-specific linear heads. We identify a resolution domain shift between the MedMNIST API and evaluation environment. Resolving this inconsistency and optimizing architecture-specific regularization substantially improved performance. Our best configuration, a ConvNeXt-Tiny backbone with label smoothing, achieved a leaderboard harmonic-mean macro-F1 of 0.73294 in the Tensor Reloaded: Multi-Task MedMNIST competition, ranking sixth at the close of the official competition phase. Our implementation is publicly available at: https://github.com/GavrilStefan-Dorian/A-Shared-Backbone-Approach-for-Multi-Task-MedMNIST-Classification
Related
- GRAMformer: Any-Order Modality Interactions via Volumetric Multimodal Cross-Attention
- BioVLM: Routing Prompts, Not Parameters, for Cross-Modality Generalization in Biomedical VLMs
- Uncertainty Identifies Difficult Samples Across Methods: A Multi-Task Study on a Heterogeneous Skin Lesion Dataset
Source: arXiv cs.CV | 2026-09-09