Abstract | ||
---|---|---|
The ability to categorize is a cornerstone of visual intelligence, and a key functionality for artificial, autonomous visual machines. This problem will never be solved without algorithms able to adapt and generalize across visual domains. Within the context of domain adaptation and generalization, this paper focuses on the predictive domain adaptation scenario, namely the case where no target data are available and the system has to learn to generalize from annotated source images plus unlabeled samples with associated metadata from auxiliary domains. Our contribution is the first deep architecture that tackles predictive domain adaptation, able to leverage over the information brought by the auxiliary domains through a graph. Moreover, we present a simple yet effective strategy that allows us to take advantage of the incoming target data at test time, in a continuous domain adaptation scenario. Experiments on three benchmark databases support the value of our approach. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/CVPR.2019.00673 | 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) |
Field | DocType | Volume |
Categorization,Graph,Metadata,Architecture,Domain adaptation,Computer science,Artificial intelligence,Cornerstone,Machine learning | Journal | abs/1903.07062 |
ISSN | Citations | PageRank |
1063-6919 | 2 | 0.36 |
References | Authors | |
16 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Massimiliano Mancini | 1 | 24 | 8.86 |
Samuel Rota Bulò | 2 | 564 | 33.69 |
Barbara Caputo | 3 | 3298 | 201.26 |
Elisa Ricci 0002 | 4 | 1393 | 73.75 |