Abstract | ||
---|---|---|
Few-shot object detection (FSOD) is a challenging task in which detectors are trained to recognize unseen objects with limited training data. The majority of existing methods are evaluated on the benchmarks built with a fixed quantity of base and novel classes categories. To be specific, the number of base classes is larger than the novel ones. This positively affects the performance evaluated on ... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/MAPR53640.2021.9585248 | 2021 International Conference on Multimedia Analysis and Pattern Recognition (MAPR) |
Keywords | DocType | ISBN |
few-shot learning,object detection,distinguished features | Conference | 978-1-6654-1910-9 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Anh-Khoa Nguyen Vu | 1 | 1 | 1.06 |
Thanh-Danh Nguyen | 2 | 0 | 1.01 |
Vinh-Tiep Nguyen | 3 | 25 | 22.31 |
Thanh Duc Ngo | 4 | 82 | 22.24 |