Object detection via a multi-region & semantic segmentation-aware CNN model
Preprint
Abstract
We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features. The resulting CNN-based representation aims at capturing a diverse set of discriminative appearance factors and exhibits localization sensitivity that is essential for accurate object localization. We exploit the above properties of our recognition module by integrating it on an iterative localization mechanism that alternates between scoring a box proposal and refining its location with a deep CNN regression model. Thanks to the efficient use of our modules, we detect objects with very high localization accuracy. On the detection challenges of PASCAL VOC2007 and PASCAL VOC2012 we achieve mAP of 78.2% and 73.9% correspondingly, surpassing any other published work by a significant margin.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- You Only Look Once: Unified, Real-Time Object Detection2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Convolutional feature masking for joint object and stuff segmentation2015
- segDeepM: Exploiting segmentation and context in deep neural networks for object detection2015
- Going deeper with convolutions2015
- DeepID-Net: Deformable deep convolutional neural networks for object detection2015
- Fully convolutional networks for semantic segmentation2015
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition2014
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004