Leveraging Internal Gradients to Understand Deep Visual Models

Mohammad Amir Asim Khan Jalwana

Research output: ThesisDoctoral Thesis

78 Downloads (Pure)

Abstract

This dissertation makes four major contributions towards the understanding of deep visual models. Firstly, it develops a model-centric technique that peeks inside the internal representation of a learned classifier. Secondly, it introduces an adversarial attack algorithm that has explicit control over the input and output domains. Thirdly, it proposes a prior-free technique to estimate high-resolution input-centric saliency maps. Lastly, it presents an algorithm that increases model robustness to adversarial perturbations. Extensive experiments demonstrate state-of-the-art performance of the proposed methods alongside their utility in many practical applications.
Original languageEnglish
QualificationDoctor of Philosophy
Awarding Institution
  • The University of Western Australia
Supervisors/Advisors
  • Mian, Ajmal, Supervisor
  • Akhtar, Naveed, Supervisor
  • Bennamoun, Mohammed, Supervisor
Award date26 Aug 2021
DOIs
Publication statusUnpublished - 2021

Fingerprint

Dive into the research topics of 'Leveraging Internal Gradients to Understand Deep Visual Models'. Together they form a unique fingerprint.

Cite this