Generic Object Detection With Dense Neural Patterns and Regionlets

Abstract

This paper addresses the challenge of establishing a bridge between deep convolutional neural networks and conventional object detection frameworks for accurate and efficient generic object detection. We introduce Dense Neural Patterns, short for DNPs, which are dense local features derived from discriminatively trained deep convolutional neural networks. DNPs can be easily plugged into conventional detection frameworks in the same way as other dense local features(like HOG or LBP). The effectiveness of the proposed approach is demonstrated with the Regionlets object detection framework. It achieved 46.1% mean average precision on the PASCAL VOC 2007 dataset, and 44.1% on the PASCAL VOC 2010 dataset, which dramatically improves the original Regionlets approach without DNPs.

References in corpus (1)

• Improving neural networks by preventing co-adaptation of feature detectors

Cited by in corpus (5)

• DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection
• ProLanGO: Protein Function Prediction Using Neural~Machine Translation Based on a Recurrent Neural Network
• Age Group and Gender Estimation in the Wild with Deep RoR Architecture
• A Deep Hashing Learning Network
• Pyramidal RoR for Image Classification