StuffNet: Using 'Stuff' to Improve Object Detection
arXiv:1610.05861
Abstract
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.
Camera-ready version for IEEE WACV 2017
References in corpus (10)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
- ParseNet: Looking Wider to See Better
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Fully Convolutional Networks for Semantic Segmentation
- Instance-aware Semantic Segmentation via Multi-task Network Cascades
- segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection
- Exploring Person Context and Local Scene Context for Object Detection
- Curriculum Learning of Multiple Tasks