Point cloud processing and 3D shape understanding are challenging tasks for which deep learning techniques have demonstrated great potentials. Still further progresses are essential to allow artificial intelligent agents to interact with the real world. In many practical conditions the amount of annotated data may be limited and integrating new sources of knowledge becomes crucial to support autonomous learning. Here we consider several scenarios involving synthetic and real world point clouds where supervised learning fails due to data scarcity and large domain gaps. We propose to enrich standard feature representations by leveraging self-supervision through a multi-task model that can solve a 3D puzzle while learning the main task of shape classification or part segmentation. An extensive analysis investigating few-shot, transfer learning and cross-domain settings shows the effectiveness of our approach with state-of-the-art results.

Joint supervised and self-supervised learning for 3D real world challenges / Alliegro, A.; Boscaini, D.; Tommasi, T.. - (2020), pp. 6718-6725. (Intervento presentato al convegno 25th International Conference on Pattern Recognition, ICPR 2020 tenutosi a Milan (Ita) nel 10-15 Jan. 2021) [10.1109/ICPR48806.2021.9412483].

Joint supervised and self-supervised learning for 3D real world challenges

Alliegro A.;Tommasi T.
2020

Abstract

Point cloud processing and 3D shape understanding are challenging tasks for which deep learning techniques have demonstrated great potentials. Still further progresses are essential to allow artificial intelligent agents to interact with the real world. In many practical conditions the amount of annotated data may be limited and integrating new sources of knowledge becomes crucial to support autonomous learning. Here we consider several scenarios involving synthetic and real world point clouds where supervised learning fails due to data scarcity and large domain gaps. We propose to enrich standard feature representations by leveraging self-supervision through a multi-task model that can solve a 3D puzzle while learning the main task of shape classification or part segmentation. An extensive analysis investigating few-shot, transfer learning and cross-domain settings shows the effectiveness of our approach with state-of-the-art results.
2020
978-1-7281-8808-9
File in questo prodotto:
File Dimensione Formato  
preprint_Joint_Supervised_and_Self-Supervised_Learning_for_3D_Real_World_Challenges.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 3.02 MB
Formato Adobe PDF
3.02 MB Adobe PDF Visualizza/Apri
Joint_Supervised_and_Self-Supervised_Learning_for_3D_Real_World_Challenges.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 3.08 MB
Formato Adobe PDF
3.08 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2923372