Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
Preprint
Abstract
Object detection systems based on the deep convolutional neural network (CNN) have recently made ground- breaking advances on several object detection benchmarks. While the features learned by these high-capacity neural networks are discriminative for categorization, inaccurate localization is still a major source of error for detection. Building upon high-capacity CNN architectures, we address the localization problem by 1) using a search algorithm based on Bayesian optimization that sequentially proposes candidate regions for an object bounding box, and 2) training the CNN with a structured loss that explicitly penalizes the localization inaccuracy. In experiments, we demonstrated that each of the proposed methods improves the detection performance over the baseline method on PASCAL VOC 2007 and 2012 datasets. Furthermore, two methods are complementary and significantly outperform the previous state-of-the-art when combined.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Structured Prediction for Object Detection in Deep Neural NetworksLecture Notes in Computer Science, 2014
- Occlusion Patterns for Object Class Detection2013
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Learning to localize detected objects2012
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012
- Diagnosing Error in Object Detectors2012
- Learning to Localize Objects with Structured Output Regression2008
- Histograms of Oriented Gradients for Human Detection2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- A Taxonomy of Global Optimization Methods Based on Response SurfacesJournal of Global Optimization, 2001