Generic Object Detection With Dense Neural Patterns and Regionlets
This work addresses the problem of accurate and efficient generic object detection for computer vision applications, representing an incremental improvement by enhancing an existing framework with new features.
The paper tackled the challenge of integrating deep convolutional neural networks with conventional object detection frameworks by introducing Dense Neural Patterns (DNPs), achieving 46.1% mAP on PASCAL VOC 2007 and 44.1% on VOC 2010, which significantly improved the original Regionlets approach.
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.