ParseNet: Looking Wider to See Better

15 Jun 2015  ·  Wei Liu, Andrew Rabinovich, Alexander 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. In addition, we study several idiosyncrasies of training, significantly increasing the performance of baseline networks (e.g. from FCN). When we add our proposed global feature, and a technique for learning normalization parameters, accuracy increases consistently even over our improved versions of the baselines. Our proposed approach, ParseNet, achieves state-of-the-art performance on SiftFlow and PASCAL-Context with small additional computational cost over baselines, and near current state-of-the-art performance on PASCAL VOC 2012 semantic segmentation with a simple approach. Code is available at https://github.com/weiliu89/caffe/tree/fcn .

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Segmentation PASCAL Context ParseNet mIoU 40.4 # 58
Semantic Segmentation PASCAL VOC 2012 test ParseNet Mean IoU 69.8% # 39

Methods


No methods listed for this paper. Add relevant methods here