KIT | KIT-Bibliothek | Impressum | Datenschutz

Self-supervised Face Representation Learning

Sharma, Vivek

This thesis investigates fine-tuning deep face features in a self-supervised manner for discriminative face representation learning, wherein we develop methods to automatically generate pseudo-labels for training a neural network. Most importantly solving this problem helps us to advance the state-of-the-art in representation learning and can be beneficial to a variety of practical downstream tasks. Fortunately, there is a vast amount of videos on the internet that can be used by machines to learn an effective representation. We present methods that can learn a strong face representation from large-scale data be the form of images or video.

However, while learning a good representation using a deep learning algorithm requires a large-scale dataset with manually curated labels, we propose self-supervised approaches to generate pseudo-labels utilizing the temporal structure of the video data and similarity constraints to get supervision from the data itself.

We aim to learn a representation that exhibits small distances between samples from the same person, and large inter-person distances in feature space. Using metric learning one could achieve that as it is comprised of a pull-term, pulling data points from the same class closer, and a push-term, pushing data points from a different class further away. ... mehr

Open Access Logo

Volltext §
DOI: 10.5445/IR/1000119819
Veröffentlicht am 02.06.2020
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Hochschulschrift
Publikationsdatum 02.06.2020
Sprache Englisch
Identifikator KITopen-ID: 1000119819
Verlag Karlsruhe
Umfang XXIII, 149 S.
Art der Arbeit Dissertation
Fakultät Fakultät für Informatik (INFORMATIK)
Institut Institut für Anthropomatik und Robotik (IAR)
Prüfungsdatum 14.05.2020
Referent/Betreuer Prof. R. Stiefelhagen
Schlagwörter Video Understanding, Video Face Clustering, Self-Supervised Learning, Representation Learning, Siamese Networks, Variational Autoencoders, Feature Encoding
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page