Traditional approaches for Visual Question Answering (VQA) require large amount of labeled data for training. Unfortunately, such large scale data is usually not available for medical domain. In this paper, we propose a novel medical VQA framework that overcomes the labeled data limitation. The proposed framework explores the use of the unsupervised Denoising Auto-Encoder (DAE) and the supervised Meta-Learning. The advantage of DAE is to leverage the large amount of unlabeled images while the advantage of Meta-Learning is to learn meta-weights that quickly adapt to VQA problem with limited labeled data. By leveraging the advantages of these techniques, it allows the proposed framework to be efficiently trained using a small labeled training set. The experimental results show that the proposed method significantly outperforms the state-of-the-art medical VQA. The source code is available at https://github.com/aioz-ai/MICCAI19-MedVQA.

No abstract

The synthesis and characterization of base-stabilized and base-free pincer-type bis(phosphine)/silylene [PSi]Ru complexes are reported. The base-free complex readily reduces CO and CSvia silylene-assisted hydride transfer, affording structurally distinct products with silicon-to-ruthenium formate and dithioformate bridges.

No abstract