2019年3月5日发表于sensors,受 Li, Z.; Peng, C.; Yu, G.; Zhang, X.; Deng, Y.; Sun, J. Light-Head R-CNN: In Defense of Two-Stage Object Detector. arXiv 2017, arXiv:1711.07264.这篇文章的启发,针对多尺度目标检测提出多层融合的轻量化检测器( multilayer fusion light-head detector ),是两阶段检测器,包括三个分支: backbone network(ResNet-101 ), region proposal subnetwork(fuses feature to detect multiscale sar ship), and light-head detection subnetwork( adapt light-head design with large-kernel separable convolution and position-sensitive pooling layer to improve the detection speed).
abstract:
- Recently, with the excellent ability of feature representation, deep neural networks such as faster region based convolution neural network (FRCN) have shown great performance in object detection tasks.
- FRCN缺点:固定感受野难以满足多尺度舰船目标,当目标很小时性能会降低;作为二阶段检测,计算量大且速度慢;复杂背景下,简单样本和困难样本的不均衡会导致高误检率。
- 本文设计 a multilayer fusion light-head detector (MFLHD) 。不使