Abstract | ||
---|---|---|
Single shot multibox detector (SSD) is a state-of-the-art network for real-time object detection. It is originally designed for general datasets. While, for specific datasets, their distribution of ground truth boxes is somehow different and thus, SSD shows unsatisfying performance. In this paper, we improve the performance of SSD on specific datasets. We first dissect the mechanism of predictors, the predicting parameters of a potential detection, in two aspects: classification and localization. Then we reveal the relationship between default boxes and predictors. With this point we finally make an improvement on default box setting and achieve a higher mAP over the original SSD on specific datasets. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1145/3177404.3177412 | PROCEEDINGS OF 2017 INTERNATIONAL CONFERENCE ON VIDEO AND IMAGE PROCESSING (ICVIP 2017) |
Keywords | Field | DocType |
predictor, SSD, default box, general datasets, specific datasets | Object detection,Pattern recognition,Computer science,Ground truth,Artificial intelligence,Detector | Conference |
Citations | PageRank | References |
0 | 0.34 | 9 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xue Mei Xie | 1 | 129 | 26.91 |
Xun Xu | 2 | 22 | 9.90 |
Lihua Ma | 3 | 0 | 0.34 |
Guangming Shi | 4 | 2663 | 184.81 |
Pengfei Chen | 5 | 62 | 13.05 |