Download PDFOpen PDF in browser

Semi-supervised Synthetic-to-Real Domain Adaptation for Fine-grained Naval Ship Image Classification

EasyChair Preprint no. 2661

11 pagesDate: February 14, 2020

Abstract

In this paper, we propose a deep learning-based approach for fine-grained naval ship image classification. To this end, we tackle following two major challenges. First, to overcome the lack of the amount of training images in the target (i.e., real) domain, we generate a large number of synthetic naval ship images by using a simulation program which is specifically designed for our task. Second, to relieve performance degradation caused by the disparity between the synthetic and the real domains, we propose a novel regularization loss, named cross-domain triplet loss. Experimental results show that both the synthetic images and the proposed cross-domain triplet loss are essential to achieve the state-of-the-art performance for fine-grained naval ship image classification.

Keyphrases: deep learning, Domain Adaptation, fine-grained classification

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@Booklet{EasyChair:2661,
  author = {Yoonhyung Kim and Hyeonjin Jang and Sangtae Park and Jiwon Lee and Changick Kim},
  title = {Semi-supervised Synthetic-to-Real Domain Adaptation for Fine-grained Naval Ship Image Classification},
  howpublished = {EasyChair Preprint no. 2661},

  year = {EasyChair, 2020}}
Download PDFOpen PDF in browser