elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Visual Similarity Detection Based on Latent Representations

Tkachuk, Kanstantsin (2021) Visual Similarity Detection Based on Latent Representations. Master's, Technical University of Munich.

[img] PDF
14MB

Abstract

In this thesis we develop and evaluate multiple scalable solutions for the task of image similarity detection as part of an automated testing system for the rendering pipeline of the game Space Engineers by GoodAI. We implement image similarity detectors based on comparison of compact representations of the input images generated by three self-supervised representation learning architectures: Multi-Path Augmented AutoEncoder by Sundermeyer et al. [12] and two kinds of Siamese networks partially based on the first architecture. We demonstrate the applicability of the aforementioned architectures in the given setting of synthetic training data and existing domain gap between the training and the application domains and evaluate their ability to produce latent representations which meet the requirements of robust generalization and invariance to variations in background, lighting, texturing and object’s pose within the field of view. We demonstrate the benefits of the multi-path architecture for the descriptiveness of latent representations with respect to the appearance features of the objects in the images as opposed to the geometric features examined in the original paper [12].

Item URL in elib:https://elib.dlr.de/185991/
Document Type:Thesis (Master's)
Title:Visual Similarity Detection Based on Latent Representations
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Tkachuk, KanstantsinUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Date:15 November 2021
Refereed publication:No
Open Access:Yes
Number of Pages:69
Status:Published
Keywords:Autoencoder, Similarity Detection, Simulation
Institution:Technical University of Munich
Department:Department of Informatics
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Robotics
DLR - Research area:Raumfahrt
DLR - Program:R RO - Robotics
DLR - Research theme (Project):R - Multisensory World Modelling (RM) [RO]
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013)
Institute of Robotics and Mechatronics (since 2013) > Perception and Cognition
Deposited By: Durner, Maximilian
Deposited On:04 Apr 2022 09:19
Last Modified:06 Dec 2022 11:07

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.