PVANet: Lightweight Deep Neural Networks for Real-time Object Detection

TL;DR

PVANet introduces a lightweight, efficient deep neural network for real-time object detection that maintains high accuracy while significantly reducing computational costs, suitable for practical applications.

Contribution

The paper presents a novel network architecture combining C.ReLU and Inception modules, achieving high accuracy with much lower computational requirements than existing models.

Findings

Achieves 84.9% mAP on VOC2007

Uses less than 10% of ResNet-101's compute

Maintains accuracy with an order of magnitude fewer parameters

Abstract

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.