Co-Domain Embedding Using Deep Quadruplet Networks for Unseen Traffic Sign Recognition

Authors

  • Junsik Kim KAIST
  • Seokju Lee KAIST
  • Tae-Hyun Oh MIT
  • In So Kweon KAIST

DOI:

https://doi.org/10.1609/aaai.v32i1.12323

Keywords:

Domain adaptation, Data Imbalance

Abstract

Recent advances in visual recognition show overarching success by virtue of large amounts of supervised data. However, the acquisition of a large supervised dataset is often challenging. This is also true for intelligent transportation applications, i.e., traffic sign recognition. For example, a model trained with data of one country may not be easily generalized to another country without much data. We propose a novel feature embedding scheme for unseen class classification when the representative class template is given. Traffic signs, unlike other objects, have official images. We perform co-domain embedding using a quadruple relationship from real and synthetic domains. Our quadruplet network fully utilizes the explicit pairwise similarity relationships among samples from different domains. We validate our method on three datasets with two experiments involving one-shot classification and feature generalization. The results show that the proposed method outperforms competing approaches on both seen and unseen classes.

Downloads

Published

2018-04-27

How to Cite

Kim, J., Lee, S., Oh, T.-H., & Kweon, I. S. (2018). Co-Domain Embedding Using Deep Quadruplet Networks for Unseen Traffic Sign Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). https://doi.org/10.1609/aaai.v32i1.12323