Exemplar-Based Open-Set Panoptic Segmentation Network
This addresses the problem of recognizing unknown objects in real-world scenes for computer vision applications, representing an incremental advancement in open-world segmentation.
The paper tackles open-set panoptic segmentation, extending it to unknown classes not seen during training, and proposes an exemplar-based network (EOPSN) that identifies new classes using clustering and similarity-based exemplar mining, demonstrating effectiveness on a constructed COCO-based benchmark.
We extend panoptic segmentation to the open-world and introduce an open-set panoptic segmentation (OPS) task. This task requires performing panoptic segmentation for not only known classes but also unknown ones that have not been acknowledged during training. We investigate the practical challenges of the task and construct a benchmark on top of an existing dataset, COCO. In addition, we propose a novel exemplar-based open-set panoptic segmentation network (EOPSN) inspired by exemplar theory. Our approach identifies a new class based on exemplars, which are identified by clustering and employed as pseudo-ground-truths. The size of each class increases by mining new exemplars based on the similarities to the existing ones associated with the class. We evaluate EOPSN on the proposed benchmark and demonstrate the effectiveness of our proposals. The primary goal of our work is to draw the attention of the community to the recognition in the open-world scenarios. The implementation of our algorithm is available on the project webpage: https://cv.snu.ac.kr/research/EOPSN.