SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving

Abstract

Object detection is a crucial task for autonomous driving. In addition to requiring high accuracy to ensure safety, object detection for autonomous driving also requires real-time inference speed to guarantee prompt vehicle control, as well as small model size and energy efficiency to enable embedded system deployment. In this work, we propose SqueezeDet, a fully convolutional neural network for object detection that aims to simultaneously satisfy all of the above constraints. In our network, we use convolutional layers not only to extract feature maps but also as the output layer to compute bounding boxes and class probabilities. The detection pipeline of our model only contains a single forward pass of a neural network, thus it is extremely fast. Our model is fully-convolutional, which leads to a small model size and better energy efficiency. While achieving the same accuracy as previous baselines, our model is 30.4x smaller, 19.7x faster, and consumes 35.2x lower energy. The code is open-sourced at \url{https://github.com/BichenWuUCB/squeezeDet}.

The supplementary material of this paper, which discusses the energy efficiency of SqueezeDet, is attached after the main paper. The source code of this work is open-source released at https://github.com/BichenWuUCB/squeezeDet

Cited by in corpus (15)

• ATRW: A Benchmark for Amur Tiger Re-identification in the Wild
• ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks
• SqueezeWave: Extremely Lightweight Vocoders for On-device Speech Synthesis
• Fusion of Multispectral Data Through Illumination-aware Deep Neural Networks for Pedestrian Detection
• Exploring the Design Space of Deep Convolutional Neural Networks at Large Scale
• Efficient Deep Neural Networks
• Low-Power Object Counting with Hierarchical Neural Networks
• Analyzing and Improving Neural Networks by Generating Semantic Counterexamples through Differentiable Rendering
• Recurrent Neural Networks for video object detection
• Weakly Supervised 3D Object Detection from Point Clouds
• Multi-criteria Evolution of Neural Network Topologies: Balancing Experience and Performance in Autonomous Systems
• Box-level Segmentation Supervised Deep Neural Networks for Accurate and Real-time Multispectral Pedestrian Detection
• Training a Binary Weight Object Detector by Knowledge Transfer for Autonomous Driving
• Metalearning: Sparse Variable-Structure Automata
• Modification method for single-stage object detectors that allows to exploit the temporal behaviour of a scene to improve detection accuracy