Deep Hashing Network for Unsupervised Domain Adaptation

Raghavendran Ramakrishnan, Bhadrinath Nagabandi, Jose Eusebio, Shayok Chakraborty, Hemanth Venkateswara, Sethuraman Panchanathan

Research output: Chapter in Book/Report/Conference proceedingChapter

4 Scopus citations

Abstract

The inadequacy of labeled data in various domains has limited the use of deep learning on several tasks. In many cases it is quite expensive in terms of both time and human effort to collect, annotate, and organize large datasets to train deep neural networks. In recent years, domain adaptation algorithms have been highly successful in leveraging labeled data from related but different datasets to build accurate classification models for unlabeled target datasets. In this chapter we present a deep learning based hashing model for domain adaptation. Hashing techniques are popular in computer vision for their efficiency in both data storage and data retrieval. We use hash-based image feature representations for robust similarity measures between features. We propose a Deep Hashing Network that is trained to learn unique hash codes by leveraging the data from both the labeled source domain and the unlabeled target domain, to correctly classify unlabeled target data. We present a detailed study of several transfer tasks across multiple datasets to corroborate the advantages of our framework.

Original languageEnglish (US)
Title of host publicationDomain Adaptation in Computer Vision with Deep Learning
PublisherSpringer International Publishing
Pages57-74
Number of pages18
ISBN (Electronic)9783030455293
ISBN (Print)9783030455286
DOIs
StatePublished - Jan 1 2020

Keywords

  • Domain adaptation
  • Entropy
  • Hashing

ASJC Scopus subject areas

  • General Computer Science
  • General Engineering

Fingerprint

Dive into the research topics of 'Deep Hashing Network for Unsupervised Domain Adaptation'. Together they form a unique fingerprint.

Cite this