ParseNet: Looking Wider to See Better

15 Jun 2015Wei LiuAndrew RabinovichAlexander C. Berg

We present a technique for adding global context to deep convolutional networks for semantic segmentation. The approach is simple, using the average feature for a layer to augment the features at each location... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Semantic Segmentation PASCAL Context ParseNet mIoU 40.4 # 13
Semantic Segmentation PASCAL VOC 2012 ParseNet Mean IoU 69.8% # 16