Exemplar-Based Open-Set Panoptic Segmentation Network
Autor: | Seoung Wug Oh, Jaedong Hwang, Bohyung Han, Joon-Young Lee |
---|---|
Rok vydání: | 2021 |
Předmět: |
FOS: Computer and information sciences
Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Image segmentation Exemplar theory Class (biology) Task (project management) Pattern recognition (psychology) Benchmark (computing) Segmentation Artificial intelligence business Cluster analysis |
Zdroj: | CVPR |
DOI: | 10.48550/arxiv.2105.08336 |
Popis: | 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. Comment: CVPR 2021 |
Databáze: | OpenAIRE |
Externí odkaz: |