Abstract | ||
---|---|---|
We consider several possible 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. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1007/978-3-030-66415-2_48 | ECCV Workshops |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Antonio Alliegro | 1 | 0 | 1.01 |
Davide Boscaini | 2 | 320 | 15.28 |
Tatiana Tommasi | 3 | 502 | 29.31 |