PVANet: Lightweight Deep Neural Networks for Real-time Object Detection
This work addresses the need for efficient real-time object detection in practical applications, representing a strong specific gain rather than a foundational advancement.
The paper tackles the problem of high computational cost in object detection by proposing PVANet, a lightweight deep neural network that is an order of magnitude lighter than state-of-the-art networks while maintaining accuracy, achieving 84.9% and 84.2% mAP on VOC2007 and VOC2012 benchmarks with less than 10% of the compute of ResNet-101.
In object detection, reducing computational cost is as important as improving accuracy for most practical usages. This paper proposes a novel network structure, which is an order of magnitude lighter than other state-of-the-art networks while maintaining the accuracy. Based on the basic principle of more layers with less channels, this new deep neural network minimizes its redundancy by adopting recent innovations including C.ReLU and Inception structure. We also show that this network can be trained efficiently to achieve solid results on well-known object detection benchmarks: 84.9% and 84.2% mAP on VOC2007 and VOC2012 while the required compute is less than 10% of the recent ResNet-101.