polito.it
Politecnico di Torino (logo)

Self-supervised contrastive learning with hard positive mining for online action detection

Matteo Latino

Self-supervised contrastive learning with hard positive mining for online action detection.

Rel. Francesco Vaccarino. Politecnico di Torino, Corso di laurea magistrale in Data Science And Engineering, 2021

[img]
Preview
PDF (Tesi_di_laurea) - Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives.

Download (3MB) | Preview
Abstract:

Supervised learning tasks require a huge amount of annotated data, that is usually hard and expensive to label. Current advancements in computer vision are moving the field toward a category of algorithms called self-supervised learning, for learning visual representations directly from unsupervised data. The goal of these techniques is to leverage non-labelled data and learn key visual representations that are useful and transferable to a set of supervised tasks. The goal of this thesis is to investigate current algorithms for learning visual representations using self-supervised approaches, and apply them to both unsupervised and supervised tasks like anomaly detection, video action detection, and objects detection, with a low annotated-data regime.

Relators: Francesco Vaccarino
Academic year: 2021/22
Publication type: Electronic
Number of Pages: 107
Subjects:
Corso di laurea: Corso di laurea magistrale in Data Science And Engineering
Classe di laurea: New organization > Master science > LM-32 - COMPUTER SYSTEMS ENGINEERING
Aziende collaboratrici: ADDFOR S.p.A
URI: http://webthesis.biblio.polito.it/id/eprint/21150
Modify record (reserved for operators) Modify record (reserved for operators)