Wide-Residual-Inception Networks for Real-time Object Detection
Authors:
- Youngwan LeeYLYoungwan Lee
- Byeonghak YimBYByeonghak Yim
- Huien KimHKHuien Kim
- Eunsoo ParkEPEunsoo Park
- Xuenan CuiXCXuenan Cui
- Taekang WooTWTaekang Woo
- Hakil KimHKHakil Kim
Preprint
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 ResNet. 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.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Identity Mappings in Deep Residual Networks2016
- Factors in Finetuning Deep Model for Object Detection with Long-Tail Distribution2016
- Convolutional neural networks at constrained time cost2015
- Deep convolutional neural fields for depth estimation from a single image2015
- Going deeper with convolutions2015
- 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
- Microsoft COCO: Common Objects in Context2014
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012