Abstract

In this paper, we propose a novel part-pair representation for part localization. In this representation, an ob ject is treated as a col- lection of part pairs to model its shape and appearance. By changing the set of pairs to be used, we are able to impose either stronger or weaker geometric constraints on the part configuration. As for the appearance, we build pair detectors for each part pair, which model the appearance of an ob ject at different levels of granularities. Our method of part local- ization exploits the part-pair representation, featuring the combination of non-parametric exemplars and parametric regression models. Non- parametric exemplars help generate reliable part hypotheses from very noisy pair detections. Then, the regression models are used to group the part hypotheses in a flexible way to predict the part locations. We eval- uate our method extensively on the dataset CUB-200-2011 [32], where we achieve significant improvement over the state-of-the-art method on bird part localization. We also experiment with human pose estimation, where our method produces comparable results to existing works.