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 (38)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Learning Face Representation by Joint Identification-Verification
• DSSD : Deconvolutional Single Shot Detector
• Going Deeper with Convolutions
• DeepID3: Face Recognition with Very Deep Neural Networks
• Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
• 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
• Convolutional Neural Networks Applied to House Numbers Digit Classification
• Submanifold Sparse Convolutional Networks
• Pay Less Attention with Lightweight and Dynamic Convolutions
• Modulating early visual processing by language
• Scene Text Detection via Holistic, Multi-Channel Prediction
• CenterNet: Keypoint Triplets for Object Detection
• Libra R-CNN: Towards Balanced Learning for Object Detection
• Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognition
• Face Detection through Scale-Friendly Deep Convolutional Networks
• Ten Years of Pedestrian Detection, What Have We Learned?
• 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
• 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
• Deep Direct Regression for Multi-Oriented Scene Text Detection
• segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection
• Real-time Universal Style Transfer on High-resolution Images via Zero-channel Pruning
• DAVE: A Unified Framework for Fast Vehicle Detection and Annotation
• PropagationNet: Propagate Points to Curve to Learn Structure Information
• A Pre-defined Sparse Kernel Based Convolution for Deep CNNs
• A Recipe for Global Convergence Guarantee in Deep Neural Networks
• Dynamically Throttleable Neural Networks (TNN)
• Semi-Supervised Noisy Student Pre-training on EfficientNet Architectures for Plant Pathology Classification
• Deep feature fusion for self-supervised monocular depth prediction
• Self-Regression Learning for Blind Hyperspectral Image Fusion Without Label
• Learning Universal Shape Dictionary for Realtime Instance Segmentation
• NeuralScale: Efficient Scaling of Neurons for Resource-Constrained Deep Neural Networks