Wide-residual-inception networks for real-time object detection
Authors:
- 1 June 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 758-764
Abstract
Since convolutional neural network (CNN) models emerged, several tasks in computer vision have actively deployed CNN models for feature extraction. However, the conventional CNN models have a high computational cost and require high memory capacity, which is impractical and unaffordable for commercial applications such as real-time on-road object detection on embedded boards or mobile platforms. To tackle this limitation of CNN models, this paper proposes a wide-residual-inception (WR-Inception) network, which constructs the architecture based on a residual inception unit that captures objects of various sizes on the same feature map, as well as shallower and wider layers, compared to state-of-the-art networks like ResNets. To verify the proposed networks, this paper conducted two experiments; one is a classification task on CIFAR-10/100 and the other is an on-road object detection task using a Single-Shot Multi-box Detector (SSD) on the KITTI dataset. WR-Inception achieves comparable accuracy on CIFAR-10/100, with test errors at 4.82% and 23.12%, respectively, which outperforms 164-layer Pre-ResNets. In addition, the detection experiments demonstrate that the WR-Inception-based SSD outperforms ResNet-101 - based SSD on KITTI. Besides, WR-Inception-based SSD achieves 16 frames per seconds, which is 3.85 times faster than ResNet-101-based SSD. We could expect WR-Inception to be used for real application systems.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Factors in Finetuning Deep Model for Object Detection with Long-Tail Distribution2016
- Fast R-CNN2015
- Factors of Transferability for a Generic ConvNet RepresentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Characterization and performance of the ASIC (CITIROC) front-end of the ASTRI cameraNuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2015
- Convolutional neural networks at constrained time cost2015
- Scalable Object Detection Using Deep Neural Networks2014
- Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012