101 0

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


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE