Similarity-based Calibration Method for Zero-Shot Recognition in Multi-object Scenes
- Title
- Similarity-based Calibration Method for Zero-Shot Recognition in Multi-object Scenes
- Author
- 최용석
- Keywords
- Zero-shot learning; similarity-based calibration; semantic embedding; knowledge graph
- Issue Date
- 2020-03
- Publisher
- ACM
- Citation
- SAC '20: Proceedings of the 35th Annual ACM Symposium on Applied Computing, Page. 1096-1103
- Abstract
- The objective of Zero-Shot Learning (ZSL) is to classify the class labels of unseen objects using external knowledge representing semantic information. Traditional zero-shot recognition models have the limitation that they rely only on the visual appearance of an unseen object. To alleviate this limitation, we propose a novel method that calibrates the visual prediction of an unseen object by using contextual information based on similarities between the unseen object and its surrounding seen objects in a multi-object scene. We incorporate the proposed method into each of the traditional models and conduct a comparative evaluation between the models with and without our calibration algorithm. The evaluation results show consistent performance improvements by a significant margin.
- URI
- https://dl.acm.org/doi/10.1145/3341105.3373931https://repository.hanyang.ac.kr/handle/20.500.11754/164982
- ISBN
- 978-1-4503-6866-7
- DOI
- 10.1145/3341105.3373931
- Appears in Collections:
- COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE(컴퓨터소프트웨어학부) > Articles
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML