Abstract | ||
---|---|---|
Convolutional neural network (CNN) is a popular choice for visual object detection where two sub-nets are often used to achieve object classification and localization separately. However, the intrinsic relation between the localization and classification sub-nets was not exploited explicitly for object detection. In this letter, we propose a novel association loss, namely, the proxy squared error (PSE) loss, to entangle the two sub-nets, thus use the dependency between the classification and localization scores obtained from these two sub-nets to improve the detection performance. We evaluate our proposed loss on the MS-COCO dataset and compare it with the loss in a recent baseline, i.e. the fully convolutional one-stage (FCOS) detector. The results show that our method can improve the AP from 33.8 to 35.4 and AP(75) from 35.4 to 37.8, as compared with the FCOS baseline. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/LSP.2020.3013160 | IEEE SIGNAL PROCESSING LETTERS |
Keywords | DocType | Volume |
Object detection, Detectors, Training, Heating systems, Feature extraction, Visualization, Convolutional neural networks, Association loss, object detection, object localization, object classification, convolutional neural networks | Journal | 27 |
ISSN | Citations | PageRank |
1070-9908 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dongli Xu | 1 | 0 | 0.34 |
GUAN Jian | 2 | 47 | 15.77 |
Pengming Feng | 3 | 33 | 4.90 |
Wenwu Wang | 4 | 333 | 52.60 |