Research Area:  Machine Learning
One-shot image semantic segmentation poses a challenging task of recognizing the object regions from unseen categories with only one annotated example as supervision. In this article, we propose a simple yet effective similarity guidance network to tackle the one-shot (SG-One) segmentation problem. We aim at predicting the segmentation mask of a query image with the reference to one densely labeled support image of the same category. To obtain the robust representative feature of the support image, we first adopt a masked average pooling strategy for producing the guidance features by only taking the pixels belonging to the support image into account. We then leverage the cosine similarity to build the relationship between the guidance features and features of pixels from the query image. In this way, the possibilities embedded in the produced similarity maps can be adopted to guide the process of segmenting objects. Furthermore, our SG-One is a unified framework that can efficiently process both support and query images within one network and be learned in an end-to-end manner. We conduct extensive experiments on Pascal VOC 2012. In particular, our SG-One achieves the mIoU score of 46.3%, surpassing the baseline methods.
Author(s) Name:  Xiaolin Zhang; Yunchao Wei; Yi Yang; Thomas S. Huang
Journal name:  IEEE Transactions on Cybernetics
Publisher name:  IEEE
Volume Information:   ( Volume: 50, Issue: 9, Sept. 2020) Page(s): 3855 - 3865
Paper Link:   https://ieeexplore.ieee.org/abstract/document/9108530