Object Detection with Deep Learning: A Review

Abstract

Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable architectures. Their performance easily stagnates by constructing complex ensembles which combine multiple low-level image features with high-level context from object detectors and scene classifiers. With the rapid development in deep learning, more powerful tools, which are able to learn semantic, high-level, deeper features, are introduced to address the problems existing in traditional architectures. These models behave differently in network architecture, training strategy and optimization function, etc. In this paper, we provide a review on deep learning based object detection frameworks. Our review begins with a brief introduction on the history of deep learning and its representative tool, namely Convolutional Neural Network (CNN). Then we focus on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further. As distinct specific detection tasks exhibit different characteristics, we also briefly survey several specific tasks, including salient object detection, face detection and pedestrian detection. Experimental analyses are also provided to compare various methods and draw some meaningful conclusions. Finally, several promising directions and tasks are provided to serve as guidelines for future work in both object detection and relevant neural network based learning systems.

References in corpus (40)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• Improving neural networks by preventing co-adaptation of feature detectors
• Caffe: Convolutional Architecture for Fast Feature Embedding
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• DSSD : Deconvolutional Single Shot Detector
• Deeply supervised salient object detection with short connections
• Learning to Segment Object Candidates
• Learning Deconvolution Network for Semantic Segmentation
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• DenseBox: Unifying Landmark Localization with End to End Object Detection
• YOLO9000: Better, Faster, Stronger
• Deformable Convolutional Networks
• Visual Saliency Detection Based on Multiscale Deep CNN Features
• Scalable, High-Quality Object Detection
• A Fast and Accurate Unconstrained Face Detector
• Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet
• Deep convolutional neural networks for pedestrian detection
• Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
• DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving
• Edge Preserving and Multi-Scale Contextual Neural Network for Salient Object Detection
• Scale-aware Fast R-CNN for Pedestrian Detection
• From Facial Parts Responses to Face Detection: A Deep Learning Approach
• DSOD: Learning Deeply Supervised Object Detectors from Scratch
• Discriminatively Trained And-Or Graph Models for Object Shape Detection
• PVANet: Lightweight Deep Neural Networks for Real-time Object Detection
• Learning Complexity-Aware Cascades for Deep Pedestrian Detection
• Multispectral Deep Neural Networks for Pedestrian Detection
• segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection
• Low-complexity Approximate Convolutional Neural Networks
• Bootstrapping Face Detection with Hard Negative Examples
• Object Detection with Pixel Intensity Comparisons Organized in Decision Trees
• DeepBox: Learning Objectness with Convolutional Networks
• Face Detection using Deep Learning: An Improved Faster RCNN Approach
• Compact Convolutional Neural Network Cascade for Face Detection
• A Multi-Scale Cascade Fully Convolutional Network Face Detector
• Multi-stage Object Detection with Group Recursive Learning
• Learning Detection with Diverse Proposals
• Learning to detect and localize many objects from few examples
• Deeply-Supervised Recurrent Convolutional Neural Network for Saliency Detection

Cited by in corpus (7)

• Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
• Computer-Aided Assessment of Catheters and Tubes on Radiographs: How Good is Artificial Intelligence for Assessment?
• Metamorphic Testing for Object Detection Systems
• A Survey on Deep Learning Methods for Semantic Image Segmentation in Real-Time
• Vulnerable road user detection: state-of-the-art and open challenges
• Phasic dopamine release identification using ensemble of AlexNet
• Dataset Bias Mitigation Through Analysis of CNN Training Scores