Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
arXiv:1809.03193
Abstract
Object detection-the computer vision task dealing with detecting instances of objects of a certain class (e.g., 'car', 'plane', etc.) in images-attracted a lot of attention from the community during the last 5 years. This strong interest can be explained not only by the importance this task has for many applications but also by the phenomenal advances in this area since the arrival of deep convolutional neural networks (DCNN). This article reviews the recent literature on object detection with deep CNN, in a comprehensive way, and provides an in-depth view of these recent advances. The survey covers not only the typical architectures (SSD, YOLO, Faster-RCNN) but also discusses the challenges currently met by the community and goes on to show how the problem of object detection can be extended. This survey also reviews the public datasets and associated state-of-the-art algorithms.
References in corpus (74)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- YOLOv3: An Incremental Improvement
- ADADELTA: An Adaptive Learning Rate Method
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- Improved Regularization of Convolutional Neural Networks with Cutout
- Striving for Simplicity: The All Convolutional Net
- The Effectiveness of Data Augmentation in Image Classification using Deep Learning
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
- DSSD : Deconvolutional Single Shot Detector
- On the Convergence of Adam and Beyond
- A Survey on Object Detection in Optical Remote Sensing Images
- Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
- One weird trick for parallelizing convolutional neural networks
- Learning from Synthetic Humans
- TextBoxes++: A Single-Shot Oriented Scene Text Detector
- Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
- Data Augmentation Generative Adversarial Networks
- Learning to Segment Object Candidates
- AutoAugment: Learning Augmentation Policies from Data
- DenseNet: Implementing Efficient ConvNet Descriptor Pyramids
- Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
- T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
- R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
- Smart Augmentation - Learning an Optimal Data Augmentation Strategy
- Facial Landmark Detection: a Literature Survey
- Beyond Skip Connections: Top-Down Modulation for Object Detection
- Scalable, High-Quality Object Detection
- Data Augmentation by Pairing Samples for Images Classification
- The EuroCity Persons Dataset: A Novel Benchmark for Object Detection
- Multimodal Unsupervised Image-to-Image Translation
- Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes
- Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
- COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
- Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
- PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection
- LSDA: Large Scale Detection Through Adaptation
- Improving Deep Learning using Generic Data Augmentation
- Seq-NMS for Video Object Detection
- Joint 3D Proposal Generation and Object Detection from View Aggregation
- Deep Learning for Logo Recognition
- Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks
- A Bayesian Data Augmentation Approach for Learning Deep Models
- Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
- LSTD: A Low-Shot Transfer Detector for Object Detection
- Object Detection with Deep Learning: A Review
- Complex-YOLO: Real-time 3D Object Detection on Point Clouds
- Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video
- Dataset Augmentation in Feature Space
- Standard detectors aren't (currently) fooled by physical adversarial stop signs
- Enhancement of SSD by concatenating feature maps for object detection
- Object Detection Using Deep CNNs Trained on Synthetic Images
- Towards High Performance Video Object Detection for Mobiles
- SFD: Single Shot Scale-invariant Face Detector
- Dual Path Networks
- On learning to localize objects with minimal supervision
- Impression Network for Video Object Detection
- A Survey of Modern Object Detection Literature using Deep Learning
- MegDet: A Large Mini-Batch Object Detector
- Zoom Out-and-In Network with Recursive Training for Object Proposal
- Residual Features and Unified Prediction Network for Single Stage Detection
- Learning Chained Deep Features and Classifiers for Cascade in Object Detection
- Exploring Person Context and Local Scene Context for Object Detection
- Extend the shallow part of Single Shot MultiBox Detector via Convolutional Neural Network
- Dynamic Zoom-in Network for Fast Object Detection in Large Images
- Wildest Faces: Face Detection and Recognition in Violent Settings
- Deep Regionlets for Object Detection
- Rank of Experts: Detection Network Ensemble
- On-the-fly Network Pruning for Object Detection
- Active learning with version spaces for object detection
- Training and Testing Object Detectors with Virtual Images
Cited by in corpus (8)
- Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
- Object Detection in 20 Years: A Survey
- DC-SPP-YOLO: Dense Connection and Spatial Pyramid Pooling Based YOLO for Object Detection
- Fast object detection in compressed JPEG Images
- Fast Region Proposal Learning for Object Detection for Robotics
- Mixup Regularization for Region Proposal based Object Detectors
- Video Logo Retrieval based on local Features
- FSD: Feature Skyscraper Detector for Stem End and Blossom End of Navel Orange