Ancestor Search: Generalized Open Set Recognition via Hyperbolic Side Information Learning

Xiwen Dengxiong, Yu Kong; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023, pp. 4003-4012

Different from the open set recognition, generalized open set recognition learns the most similar known classes for unseen samples using known classes samples and side information of known classes. It is challenging because hierarchically structured side information is distorted when features are embedded in the Euclidean space in existing literature, which incurs the difficulty of identifying the unseen samples. In this paper, we introduce a side information learning algorithm for generalized open set recognition based on the hyperbolic space to alleviate the distortion and accurately identify the unknown samples. Specifically, we propose a hyperbolic side information learning framework to identify the unseen samples and an ancestor search algorithm to search the most similar ancestor from the taxonomy of selected known classes. Experiments on CUB-200 and AWA 2 datasets show that our method improves the performance of generalized open set recognition by a large margin.