INSTITUTIONAL DIGITAL REPOSITORY

Browsing by Author "Sukhija, S."

Browsing by Author "Sukhija, S."

Sort by: Order: Results:

  • Image encryption based on watermarking technique in fourier domain using pixel scrambling 
    Dahiya, M.; Sukhija, S.; Kumar, D.; Singh, H. (2021-10-19)
    In this paper a technique has been proposed that enhances the security level by concealing an image inside another. The method uses Fourier transform with random phase masks to make it imperceptible by obscuring the ...
  • Label space driven feature space remapping 
    Sukhija, S. (2018-11-13)
    The elicitation of labeled training data from physical sources is a primary bottleneck that limits the applicability of traditional supervised learning algorithms. Transfer learning algorithms overcome the limitation ...
  • Label space driven heterogeneous transfer learning with web induced alignment 
    Sukhija, S. (2019-05-20)
    Heterogeneous Transfer Learning (HTL) algorithms leverage knowledge from a heterogeneous source domain to perform a task in a target domain. We present a novel HTL algorithm that works even where there are no shared ...
  • Leveraging label-space similarities for transfer learning 
    Sukhija, S. (2020-10-05)
    Human learning revolves around experiences. The gradual acquisition of knowledge for learning a new task involves leveraging similar experiences in the past. The capability to transfer prior knowledge to generalize to ...
  • Multi-Partition feature alignment network for unsupervised domain adaptation 
    Sukhija, S.; Varadarajan, S.; Krishnan, K. C.; Rai, S. (2021-07-03)
    In this paper, we present a novel unsupervised domain adaptation framework, Multi-Partition Feature Alignment Network, that learns a deep neural model for the target domain without the need for any supervision. Recent ...
  • Supervised heterogeneous domain adaptation via random forests 
    Sukhija, S.; Krishnan, N. C.; Singh, G. (2021-10-04)
    Heterogeneity of features and lack of correspondence between data points of different domains are the two primary challenges while performing feature transfer. In this paper, we present a novel supervised domain adaptation ...
  • Supervised heterogeneous feature transfer via random forests 
    Sukhija, S.; Narayanan, C.K. (2018-12-20)
    Transfer learning across heterogeneous feature spaces can, in general, be a very difficult problem in practice due to the heterogeneity of features and lack of correspondence between data points of different domains. In ...
  • Supervised heterogeneous transfer learning using random forests 
    Sukhija, S.; Krishnan, N.C.; Kumar, D. (2018-12-20)
    Supervised transfer learning algorithms utilize labeled data from auxiliary domains for learning in another domain where labeled data is scarce or absent. Given sufficient cross-domain corresponding instances, one can ...