Deep Reasoning Network for Few-shot Semantic Segmentation

Few-shot Semantic Segmentation (FSS) is a challenging problem in computer vision, which aims at segmenting objects of interest with only one or several annotated samples per category for training. The essence of FSS is to disseminate information from support images to query images for segmenting the mutual object categories. In this paper, we propose a Dynamic Reasoning Network (DRNet) to adaptively generate the parameters of predicting layers and infer the segmentation mask for each unseen category. More specifically, an Attentional Feature Integration Sub-network (AFIS) is first proposed to extract consistent features from support images and query images. With shared weights, it stimulates the category consistency of different data streams. Then, a Pooling-based Guidance Module (PGM) is used to correlate support features with query features progressively. To disseminate information from support images to various query images, we further propose a Dynamic Prediction Module (DPM) for generating the parameters of predicting layers. The proposed modules are unified for the dynamic reasoning of each query image segmentation. Experiments on two public benchmarks have demonstrated that our approach achieves superior performance and outperforms the recent state-of-the-art methods.