A Survey of Modern Object Detection Literature using Deep Learning

Object detection is the identification of an object in the image along with its localisation and classification. It has wide spread applications and is a critical component for vision based software systems. This paper seeks to perform a rigorous survey of modern object detection algorithms that use deep learning. As part of the survey, the topics explored include various algorithms, quality metrics, speed/size trade offs and training methodologies. This paper focuses on the two types of object detection algorithms- the SSD class of single step detectors and the Faster R-CNN class of two step detectors. Techniques to construct detectors that are portable and fast on low powered devices are also addressed by exploring new lightweight convolutional base architectures. Ultimately, a rigorous review of the strengths and weaknesses of each detector leads us to the present state of the art.

• Publication year

  2018

• Venue

  arXiv.org

• Publication date

  2018-08-22

• Fields of study

  Computer Science, Engineering

• Identifiers
  arXiv 1808.07256
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Averaging Weights Leads to Wider Optima and Better Generalization

  2018cited by this paper
• Effnet: An Efficient Structure for Convolutional Neural Networks

  2018cited by this paper
• DARTS: Differentiable Architecture Search

  2018cited by this paper
• A disciplined approach to neural network hyper-parameters: Part 1 - learning rate, batch size, momentum, and weight decay

  2018cited by this paper
• Pooling Pyramid Network for Object Detection

  2018cited by this paper
• Quantizing deep convolutional networks for efficient inference: A whitepaper

  2018cited by this paper
• Efficient Neural Architecture Search via Parameter Sharing

  2018cited by this paper
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

  2017cited by this paper
• Super-Convergence: Very Fast Training of Residual Networks Using Large Learning Rates

  2017influential reference
• Focal Loss for Dense Object Detection

  2017cited by this paper
• DSSD : Deconvolutional Single Shot Detector

  2017cited by this paper
• Training Region-Based Object Detectors with Online Hard Example Mining

  2016cited by this paper
• SGDR: Stochastic Gradient Descent with Warm Restarts

  2016cited by this paper
• Feature Pyramid Networks for Object Detection

  2016cited by this paper
• YOLO9000: Better, Faster, Stronger

  2016influential reference
• Region-Based Convolutional Networks for Accurate Object Detection and Segmentation

  2016cited by this paper
• Fast R-CNN

  2015influential reference
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• SSD: Single Shot MultiBox Detector

  2015influential reference
• You Only Look Once: Unified, Real-Time Object Detection

  2015cited by this paper
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

  2015cited by this paper
• Cyclical Learning Rates for Training Neural Networks

  2015cited by this paper
• Caffe: Convolutional Architecture for Fast Feature Embedding

  2014cited by this paper
• Fully convolutional networks for semantic segmentation

  2014cited by this paper
• Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

  2013influential reference
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

  2013cited by this paper
• Selective Search for Object Recognition

  2013cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• Cascade object detection with deformable part models

  2010cited by this paper
• The Pascal Visual Object Classes (VOC) Challenge

  2010cited by this paper
• Learning and example selection for object and pattern detection

  1996cited by this paper
• Human Face Detection in Visual Scenes

  1995cited by this paper

• Sperm Detection Based on You Only Look Once-Neural Architecture Search (YOLO-NAS)

  2026cites this paper
• Object Detection Based on CNN and Vision-Transformer: A Survey

  2025cites this paper
• Not all fog removers are equal: Unmasking the impact of dehazing on object detection

  2025cites this paper
• Deep Learning Applications in MRI-Based Detection of the Hippocampal Region for Alzheimer’s Diagnosis

  2024cites this paper
• Optimizing Handwritten Digit Recognition with CNN and Data Augmentation Strategies

  2024cites this paper
• Real-Time 3D Routing Optimization for Unmanned Aerial Vehicle using Machine Learning

  2024cites this paper
• VGG-SSD Model for Weapon Detection using Image Processing

  2024cites this paper
• A Comprehensive Study on Explainable AI Using YOLO and Post Hoc Method on Medical Diagnosis

  2024cites this paper
• Deep Learning for Computer Vision: Innovations in Image Recognition and Processing Techniques

  2024cites this paper
• Research on Real-time Detection of Stacked Objects Based on Deep Learning

  2023cites this paper
• Benchmarks: Semantic Segmentation Neural Network Verification and Objection Detection Neural Network Verification in Perceptions Tasks of Autonomous Driving

  2023cites this paper
• An intelligent framework to detect and generate alert while cattle lying on road in dangerous states using surveillance videos

  2023cites this paper
• Building Envelope Object Detection Using YOLO Models

  2022cites this paper
• Tree Trunk Recognition in Orchard Autonomous Operations under Different Light Conditions Using a Thermal Camera and Faster R-CNN

  2022cites this paper
• Multiple Object Tracking using STMRF and YOLOv4 Deep SORT in Surveillance Video

  2022cites this paper
• Deep Learning-based Small Object Detection: A Survey

  2022cites this paper
• Detecting Vehicles on the Edge: Knowledge Distillation to Improve Performance in Heterogeneous Road Traffic

  2022cites this paper
• Malaria parasites detection and identification using object detectors based on deep neural networks: a wide comparative analysis

  2022cites this paper
• DeepCADD: A Deep Learning Architecture for Automatic Detection of Coronary Artery Disease

  2022influential citation
• Deep Learning-Based Object Detection Approach for Autonomous Vehicles

  2022cites this paper
• Machine Learning Approach to Real-Time 3D Path Planning for Autonomous Navigation of Unmanned Aerial Vehicle

  2021cites this paper
• YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs

  2021cites this paper
• On-Device Object Detection for More Efficient and Privacy-Compliant Visual Perception in Context-Aware Systems

  2021influential citation
• Optimized convolutional neural network architectures for efficient on-device vision-based object detection

  2021cites this paper
• Convolutional Neural Networks for Underwater Pipeline Segmentation using Imperfect Datasets

  2021cites this paper
• Object Detection using Deep Learning: A Review

  2021influential citation
• Fast Mumford-Shah Two-Phase Image Segmentation Using Proximal Splitting Scheme

  2021cites this paper
• Object Detection Combining CNN and Adaptive Color Prior Features

  2021cites this paper
• A Survey of Modern Deep Learning based Object Detection Models

  2021cites this paper
• Single Shot Multibox Detector With Deconvolutional Region Magnification Procedure

  2021cites this paper
• Human-Machine Cooperative Video Anomaly Detection

  2020cites this paper
• Identification and Classification of Trucks and Trailers on the Road Network through Deep Learning

  2019cites this paper
• An Approach Combined the Faster RCNN and Mobilenet for Logo Detection

  2019cites this paper
• A Novel Effectively Optimized One-Stage Network for Object Detection in Remote Sensing Imagery

  2019cites this paper
• Evaluation of Multiple Object Tracking in Surveillance Video

  2019influential citation
• Prediction Model of Scoliosis Progression Bases on Deep Learning

  2019cites this paper
• Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks

  2018cites this paper
• Benchmarking Formal Verification for Autonomous Driving in the Wild

  year unknowncites this paper