A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets

Abstract

This survey paper specially analyzed computer vision-based object detection challenges and solutions by different techniques. We mainly highlighted object detection by three different trending strategies, i.e., 1) domain adaptive deep learning-based approaches (discrepancy-based, Adversarial-based, Reconstruction-based, Hybrid). We examined general as well as tiny object detection-related challenges and offered solutions by historical and comparative analysis. In part 2) we mainly focused on tiny object detection techniques (multi-scale feature learning, Data augmentation, Training strategy (TS), Context-based detection, GAN-based detection). In part 3), To obtain knowledge-able findings, we discussed different object detection methods, i.e., convolutions and convolutional neural networks (CNN), pooling operations with trending types. Furthermore, we explained results with the help of some object detection algorithms, i.e., R-CNN, Fast R-CNN, Faster R-CNN, YOLO, and SSD, which are generally considered the base bone of CV, CNN, and OD. We performed comparative analysis on different datasets such as MS-COCO, PASCAL VOC07,12, and ImageNet to analyze results and present findings. At the end, we showed future directions with existing challenges of the field. In the future, OD methods and models can be analyzed for real-time object detection, tracking strategies.

References in corpus (94)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• A Survey on Deep Learning in Medical Image Analysis
• YOLOv3: An Incremental Improvement
• Spectral Normalization for Generative Adversarial Networks
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Instance Normalization: The Missing Ingredient for Fast Stylization
• MobileNetV2: Inverted Residuals and Linear Bottlenecks
• Deep Visual Domain Adaptation: A Survey
• Wide Residual Networks
• Deep Learning Face Representation by Joint Identification-Verification
• DSSD : Deconvolutional Single Shot Detector
• A Survey on Object Detection in Optical Remote Sensing Images
• Going Deeper with Convolutions
• A Survey of Deep Learning-based Object Detection
• A guide to convolution arithmetic for deep learning
• An Introduction to Convolutional Neural Networks
• DeepID3: Face Recognition with Very Deep Neural Networks
• Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
• A review of domain adaptation without target labels
• T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
• Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks
• Object Detection in 20 Years: A Survey
• R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
• Adversarial Discriminative Domain Adaptation
• TextBoxes: A Fast Text Detector with a Single Deep Neural Network
• The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
• Aggregated Residual Transformations for Deep Neural Networks
• Convolutional Neural Networks Applied to House Numbers Digit Classification
• Submanifold Sparse Convolutional Networks
• Vision Meets Drones: A Challenge
• MixConv: Mixed Depthwise Convolutional Kernels
• Pay Less Attention with Lightweight and Dynamic Convolutions
• Modulating early visual processing by language
• Wasserstein Distance Guided Representation Learning for Domain Adaptation
• Deep convolutional neural networks for pedestrian detection
• Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
• Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
• Scene Text Detection via Holistic, Multi-Channel Prediction
• Glow: Generative Flow with Invertible 1x1 Convolutions
• CenterNet: Keypoint Triplets for Object Detection
• Borrow from Anywhere: Pseudo Multi-modal Object Detection in Thermal Imagery
• Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
• HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
• Libra R-CNN: Towards Balanced Learning for Object Detection
• Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognition
• EAST: An Efficient and Accurate Scene Text Detector
• Face Detection through Scale-Friendly Deep Convolutional Networks
• A System for Automatic Rice Disease Detection from Rice Paddy Images Serviced via a Chatbot
• FT-CNN: Algorithm-Based Fault Tolerance for Convolutional Neural Networks
• Ten Years of Pedestrian Detection, What Have We Learned?
• Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment
• Selective Kernel Networks
• Perceptual Generative Adversarial Networks for Small Object Detection
• SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses
• How Far are We from Solving Pedestrian Detection?
• LOGO-Net: Large-scale Deep Logo Detection and Brand Recognition with Deep Region-based Convolutional Networks
• Domain Adaptation for Object Detection via Style Consistency
• Single Shot Text Detector with Regional Attention
• Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
• SNIPER: Efficient Multi-Scale Training
• Deep Direct Regression for Multi-Oriented Scene Text Detection
• segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection
• PyramidBox: A Context-assisted Single Shot Face Detector
• Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation
• Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
• Deformable Object Tracking with Gated Fusion
• Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning
• Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships
• Learning Cross-Modal Deep Representations for Robust Pedestrian Detection
• SFA: Small Faces Attention Face Detector
• Repulsion Loss: Detecting Pedestrians in a Crowd
• COVID-19 detection using chest X-rays: is lung segmentation important for generalization?
• Real-time Universal Style Transfer on High-resolution Images via Zero-channel Pruning
• AttentionNet: Aggregating Weak Directions for Accurate Object Detection
• DR Loss: Improving Object Detection by Distributional Ranking
• DAVE: A Unified Framework for Fast Vehicle Detection and Annotation
• PropagationNet: Propagate Points to Curve to Learn Structure Information
• SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection
• A Pre-defined Sparse Kernel Based Convolution for Deep CNNs
• Comprehensive Comparison of Deep Learning Models for Lung and COVID-19 Lesion Segmentation in CT scans
• Dynamically Throttleable Neural Networks (TNN)
• A Recipe for Global Convergence Guarantee in Deep Neural Networks
• Semi-Supervised Noisy Student Pre-training on EfficientNet Architectures for Plant Pathology Classification
• Concept Mask: Large-Scale Segmentation from Semantic Concepts
• Algorithm-hardware Co-design for Deformable Convolution
• Deep feature fusion for self-supervised monocular depth prediction
• Rethinking Neural Operations for Diverse Tasks
• Self-Regression Learning for Blind Hyperspectral Image Fusion Without Label
• TS-Net: OCR Trained to Switch Between Text Transcription Styles
• NeuralScale: Efficient Scaling of Neurons for Resource-Constrained Deep Neural Networks
• Learning Universal Shape Dictionary for Realtime Instance Segmentation
• Conditioning Trick for Training Stable GANs
• Extract and Merge: Merging extracted humans from different images utilizing Mask R-CNN