Fixed-Point Model For Structured Labeling
Quannan Li, Jingdong Wang, David Wipf, Zhuowen Tu · 2013
In this paper, we propose a simple but effec-tive solution to the structured labeling prob-lem: a fixed-point model. Recently, layered models with sequential classifiers/regressors have gained an increasing amount of interests for structural prediction. Here, we design an algorithm with a new perspective on layered models; we aim to find a fixed-point func-tion with the structured labels being both the output and the input. Our approach allevi-ates the burden in learning multiple/different classifiers in different layers. We devise a training strategy for our method and pro-vide justifications for the fixed-point function to be a contraction mapping. The learned function captures rich contextual information and is easy to train and test. On several widely used benchmark datasets, the pro-posed method observes significant improve-ment in both performance and efficiency over many state-of-the-art algorithms. 1.