Abstract | ||
---|---|---|
Modern CNN-based object detectors assign anchors for ground-truth objects under the restriction of object-anchor Intersection-over-Union (IoU). In this study, we propose a learning-to-match (LTM) method to break IoU restriction, allowing objects to match anchors in a flexible manner. LTM updates hand-crafted anchor assignment to “free” anchor matching by formulating detector training in the Maximu... |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TPAMI.2021.3050494 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Keywords | DocType | Volume |
Detectors,Location awareness,Feature extraction,Training,Maximum likelihood estimation,Object detection,Visualization | Journal | 44 |
Issue | ISSN | Citations |
6 | 0162-8828 | 4 |
PageRank | References | Authors |
0.47 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiao-song Zhang | 1 | 305 | 45.10 |
Fang Wan | 2 | 21 | 3.44 |
Chang Liu | 3 | 571 | 117.41 |
Xiangyang Ji | 4 | 533 | 73.14 |
Qixiang Ye | 5 | 913 | 64.51 |