Deep Learning for Generic Object Detection: A Survey

Abstract

Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images. Deep learning techniques have emerged as a powerful strategy for learning feature representations directly from data and have led to remarkable breakthroughs in the field of generic object detection. Given this period of rapid evolution, the goal of this paper is to provide a comprehensive survey of the recent achievements in this field brought about by deep learning techniques. More than 300 research contributions are included in this survey, covering many aspects of generic object detection: detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics. We finish the survey by identifying promising directions for future research.

IJCV Minor

References in corpus (55)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• A Survey on Deep Learning in Medical Image Analysis
• Distilling the Knowledge in a Neural Network
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Neural Architecture Search with Reinforcement Learning
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• How transferable are features in deep neural networks?
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• Conditional Random Fields as Recurrent Neural Networks
• DSSD : Deconvolutional Single Shot Detector
• Graph Neural Networks: A Review of Methods and Applications
• Recent Trends in Deep Learning Based Natural Language Processing
• Binarized Neural Networks
• What makes for effective detection proposals?
• Learning to Segment Object Candidates
• Pruning Filters for Efficient ConvNets
• Return of the Devil in the Details: Delving Deep into Convolutional Nets
• High-Resolution Representations for Labeling Pixels and Regions
• Learning multiple visual domains with residual adapters
• Associative Embedding: End-to-End Learning for Joint Detection and Grouping
• Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
• Deformable Convolutional Networks
• The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
• Beyond Skip Connections: Top-Down Modulation for Object Detection
• Scalable, High-Quality Object Detection
• DetNet: A Backbone network for Object Detection
• PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection
• Learning the Number of Neurons in Deep Networks
• Few-Example Object Detection with Model Communication
• Hybrid Task Cascade for Instance Segmentation
• Path-Level Network Transformation for Efficient Architecture Search
• HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
• Learning RoI Transformer for Detecting Oriented Objects in Aerial Images
• Locally Scale-Invariant Convolutional Neural Networks
• DSOD: Learning Deeply Supervised Object Detectors from Scratch
• Analyzing the Performance of Multilayer Neural Networks for Object Recognition
• segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection
• Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection
• RepMet: Representative-based metric learning for classification and one-shot object detection
• Oriented Response Networks
• Dual Path Networks
• An end-to-end TextSpotter with Explicit Alignment and Attention
• WIDER Face and Pedestrian Challenge 2018: Methods and Results
• Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships
• Towards Universal Object Detection by Domain Attention
• DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers
• Zero-Shot Object Detection by Hybrid Region Embedding
• ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond
• Modeling Visual Context is Key to Augmenting Object Detection Datasets

Cited by in corpus (46)

• Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
• A Survey of Autonomous Driving: Common Practices and Emerging Technologies
• Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges
• A Survey of Deep Learning-based Object Detection
• Object Detection in 20 Years: A Survey
• Denoising Prior Driven Deep Neural Network for Image Restoration
• Grape detection, segmentation and tracking using deep neural networks and three-dimensional association
• Medical Deep Learning -- A systematic Meta-Review
• Enabling and Emerging Technologies for Social Distancing: A Comprehensive Survey and Open Problems
• Machine learning in nuclear materials research
• Deep Learning Classification of 3.5 GHz Band Spectrograms with Applications to Spectrum Sensing
• Scene Text Detection and Recognition: The Deep Learning Era
• Review of data analysis in vision inspection of power lines with an in-depth discussion of deep learning technology
• Angle-Closure Detection in Anterior Segment OCT based on Multi-Level Deep Network
• A Deep Learning Based Automatic Defect Analysis Framework for In-situ TEM Ion Irradiations
• XAIR: A Framework of Explainable AI in Augmented Reality
• Multi defect detection and analysis of electron microscopy images with deep learning
• Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection
• Daedalus: Breaking Non-Maximum Suppression in Object Detection via Adversarial Examples
• Camouflaged Object Segmentation with Distraction Mining
• DeepMTL Pro: Deep Learning Based MultipleTransmitter Localization and Power Estimation
• Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review
• Driving Datasets Literature Review
• Metamorphic Testing for Object Detection Systems
• Seeing isn't Believing: Practical Adversarial Attack Against Object Detectors
• Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving
• Fine-Tuning and Training of DenseNet for Histopathology Image Representation Using TCGA Diagnostic Slides
• A Review on Intelligent Object Perception Methods Combining Knowledge-based Reasoning and Machine Learning
• DotHash: Estimating Set Similarity Metrics for Link Prediction and Document Deduplication
• Comparison-Based Convolutional Neural Networks for Cervical Cell/Clumps Detection in the Limited Data Scenario
• Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection
• Learning to discover and localize visual objects with open vocabulary
• Automated Rip Current Detection with Region based Convolutional Neural Networks
• Detection Method Based on Automatic Visual Shape Clustering for Pin-Missing Defect in Transmission Lines
• Performance, Successes and Limitations of Deep Learning Semantic Segmentation of Multiple Defects in Transmission Electron Micrographs
• Understanding the Effects of Pre-Training for Object Detectors via Eigenspectrum
• Efficient Object Embedding for Spliced Image Retrieval
• Min-Entropy Latent Model for Weakly Supervised Object Detection
• Towards Early Prediction of Human iPSC Reprogramming Success
• Real time expert system for anomaly detection of aerators based on computer vision technology and existing surveillance cameras
• From abstract items to latent spaces to observed data and back: Compositional Variational Auto-Encoder
• Deep Learning-Assisted Localisation of Nanoparticles in synthetically generated two-photon microscopy images
• Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering
• FSD: Feature Skyscraper Detector for Stem End and Blossom End of Navel Orange
• Empirical Upper Bound, Error Diagnosis and Invariance Analysis of Modern Object Detectors
• Object Detection and Recognition of Swap-Bodies using Camera mounted on a Vehicle