StuffNet: Using 'Stuff' to Improve Object Detection
2017 IEEE Winter Conference on Applications of Computer Vision (WACV)(2017)
摘要
We propose a Convolutional Neural Network (CNN) based algorithm - StuffNet - for object detection. In addition to the standard convolutional features trained for region proposal and object detection [31], StuffNet uses convolutional features trained for segmentation of objects and 'stuff' (amorphous categories such as ground and water). Through experiments on Pascal VOC 2010, we show the importance of features learnt from stuff segmentation for improving object detection performance. StuffNet improves performance from 18.8% mAP to 23.9% mAP for small objects. We also devise a method to train StuffNet on datasets that do not have stuff segmentation labels. Through experiments on Pascal VOC 2007 and 2012, we demonstrate the effectiveness of this method and show that StuffNet also significantly improves object detection performance on such datasets.
更多查看译文
关键词
convolutional neural network based algorithm,CNN-based algorithm,standard convolutional features,region proposal,object segmentation,Pascal VOC 2010,feature learning,stuff segmentation,object detection performance improvement,StuffNet training,Pascal VOC 2007,Pascal VOC 2012
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络