1k citations · 1.2k across the 2 of their papers we have counts for
2 papers
cs.CV2015★ 147 cited
BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
Jifeng Dai, Kaiming He, Jian Sun
Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks. Such pixel-accurate supervision…
cs.CV2015★ 1k cited
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Kaiming He, Xiangyu Zhang, Shaoqing Ren +1
Rectified activation units (rectifiers) are essential for state-of-the-art neural networks. In this work, we study rectifier neural networks for image classification from two aspec…