- GENet(更泛化的SEnet,有带参数和不参数的模块)
SENet之后,Jie Hu和Li Shen等人又提出GENet[1]。单位:Momenta, Visual Geometry Group University of Oxford ;
[1] Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks NIPS 2018 [paper][code]
- ESPNet/V2 (v1针对分割任务,就是先用pointwise卷积,然后用金字塔的空洞卷积,HFF(Hier feature fusion),v2更泛化的模块->针对mobileNet and shufflenet)
原文链接:https://arxiv.org/abs/1803.06815v2
相关repo:https://github.com/sacmehta/ESPNet
论文学习笔记(四)ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation