Attention-driven Tree-structured Convolutional LSTM for High Dimensional Data Understanding
Abstract
Modeling the sequential information of image sequences has been a vital step of various vision tasks and convolutional long short-term memory (ConvLSTM) has demonstrated its superb performance in such spatiotemporal problems. Nevertheless, the hierarchical data structures in a significant amount of tasks (e.g., human body parts and vessel/airway tree in biomedical images) cannot be properly modeled by sequential models. Thus, ConvLSTM is not suitable for tree-structured image data analysis. In order to address these limitations, we present tree-structured ConvLSTM models for tree-structured image analysis tasks which can be trained end-to-end. To demonstrate the effectiveness of the proposed tree-structured ConvLSTM model, we present a tree-structured segmentation framework which consists of a tree-structured ConvLSTM and an attention fully convolutional network (FCN) model. The proposed framework is extensively validated on four large-scale coronary artery datasets. The results demonstrate the effectiveness and efficiency of the proposed method.
Cite
@article{arxiv.1902.10053,
title = {Attention-driven Tree-structured Convolutional LSTM for High Dimensional Data Understanding},
author = {Bin Kong and Xin Wang and Junjie Bai and Yi Lu and Feng Gao and Kunlin Cao and Qi Song and Shaoting Zhang and Siwei Lyu and Youbing Yin},
journal= {arXiv preprint arXiv:1902.10053},
year = {2019}
}