Unsupervised landmark discovery via self-training correspondence

Mallis, Dimitrios (2023) Unsupervised landmark discovery via self-training correspondence. PhD thesis, University of Nottingham.

[thumbnail of Thesis_Mallis_revised_version.pdf]
Preview
PDF (Thesis - as examined) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Available under Licence Creative Commons Attribution.
Download (29MB) | Preview

Abstract

Object parts, also known as landmarks, convey information about an object’s shape and spatial configuration in 3D space, especially for deformable objects. The goal of landmark detection is to have a model that, for a particular object instance, can estimate the locations of its parts. Research in this field is mainly driven by supervised approaches, where a sufficient amount of human-annotated data is available. As annotating landmarks for all objects is impractical, this thesis focuses on learning landmark detectors without supervision. Despite good performance on limited scenarios (objects showcasing minor rigid deformation), unsupervised landmark discovery mostly remains an open problem. Existing work fails to capture semantic landmarks, i.e. points similar to the ones assigned by human annotators and may not generalise well to highly articulated objects like the human body, complicated backgrounds or large viewpoint variations.

In this thesis, we propose a novel self-training framework for the discovery of unsupervised landmarks. Contrary to existing methods that build on auxiliary tasks such as image generation or equivariance, we depart from generic keypoints and train a landmark detector and descriptor to improve itself, tuning the keypoints into distinctive landmarks. We propose an iterative algorithm that alternates between producing new pseudo-labels through feature clustering and learning distinctive features for each pseudo-class through contrastive learning. Our detector can discover highly semantic landmarks, that are more flexible in terms of capturing large viewpoint changes and out-of-plane rotations (3D rotations). New state-of-the-art performance is achieved in multiple challenging datasets.

Item Type: Thesis (University of Nottingham only) (PhD)
Supervisors: Tzimiropoulos, Georgios
Bell, Matt
Keywords: unsupervised Landmark discovery, self-training, clustering correspondence, keypoints
Subjects: Q Science > QA Mathematics > QA 75 Electronic computers. Computer science
Faculties/Schools: UK Campuses > Faculty of Science > School of Computer Science
Related URLs:
Item ID: 72953
Depositing User: Mallis, Dimitrios
Date Deposited: 26 Jul 2023 04:40
Last Modified: 26 Jul 2023 04:40
URI: https://eprints.nottingham.ac.uk/id/eprint/72953

Actions (Archive Staff Only)

Edit View Edit View