segDeepM: Exploiting segmentation and context in deep neural networks for object detection
Authors:
- 1 June 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 4703-4711
Abstract
In this paper, we propose an approach that exploits object segmentation in order to improve the accuracy of object detection. We frame the problem as inference in a Markov Random Field, in which each detection hypothesis scores object appearance as well as contextual information using Convolutional Neural Networks, and allows the hypothesis to choose and score a segment out of a large pool of accurate object segmentation proposals. This enables the detector to incorporate additional evidence when it is available and thus results in more accurate detections. Our experiments show an improvement of 4.1% in mAP over the R-CNN baseline on PASCAL VOC 2010, and 3.4% over the current state-of-the-art, demonstrating the power of our approach.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- The Role of Context for Object Detection and Semantic Segmentation in the Wild2014
- Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts2014
- DeepFlow: Large Displacement Optical Flow with Deep Matching2013
- Bottom-Up Segmentation for Top-Down Detection2013
- Object detection and segmentation from joint embedding of parts and pixels2011
- Segmentation as selective search for object recognition2011
- The truth about cats and dogs2011
- Constrained parametric min-cuts for automatic object segmentation2010
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009