A Comparison of Pre-trained Vision-and-Language Models for Multimodal Representation Learning across Medical Images and Reports
arXiv:2009.01523
Abstract
Joint image-text embedding extracted from medical images and associated contextual reports is the bedrock for most biomedical vision-and-language (V+L) tasks, including medical visual question answering, clinical image-text retrieval, clinical report auto-generation. In this study, we adopt four pre-trained V+L models: LXMERT, VisualBERT, UNIER and PixelBERT to learn multimodal representation from MIMIC-CXR radiographs and associated reports. The extrinsic evaluation on OpenI dataset shows that in comparison to the pioneering CNN-RNN model, the joint embedding learned by pre-trained V+L models demonstrate performance improvement in the thoracic findings classification task. We conduct an ablation study to analyze the contribution of certain model components and validate the advantage of joint embedding over text-only embedding. We also visualize attention maps to illustrate the attention mechanism of V+L models.
arXiv comment10 pages, 3 figures, submitted to BIBM2020
References in corpus (12)
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
- VisualBERT: A Simple and Performant Baseline for Vision and Language
- Publicly Available Clinical BERT Embeddings
- Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
- Aggregated Residual Transformations for Deep Neural Networks
- Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers
- LXMERT: Learning Cross-Modality Encoder Representations from Transformers
- UNITER: UNiversal Image-TExt Representation Learning
- Unsupervised Multimodal Representation Learning across Medical Images and Reports
- Lessons from Natural Language Inference in the Clinical Domain
- Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models