Domain Adaptation for Visual Applications: A Comprehensive Survey

Abstract

The aim of this paper is to give an overview of domain adaptation and transfer learning with a specific view on visual applications. After a general motivation, we first position domain adaptation in the larger transfer learning problem. Second, we try to address and analyze briefly the state-of-the-art methods for different types of scenarios, first describing the historical shallow methods, addressing both the homogeneous and the heterogeneous domain adaptation methods. Third, we discuss the effect of the success of deep convolutional architectures which led to new type of domain adaptation methods that integrate the adaptation within the deep architecture. Fourth, we overview the methods that go beyond image categorization, such as object detection or image segmentation, video analyses or learning visual attributes. Finally, we conclude the paper with a section where we relate domain adaptation to other machine learning solutions.

Book chapter to appear in "Domain Adaptation in Computer Vision Applications", Springer Series: Advances in Computer Vision and Pattern Recognition, Edited by Gabriela Csurka

References in corpus (26)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Deep Domain Confusion: Maximizing for Domain Invariance
• Frustratingly Easy Domain Adaptation
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
• A Survey on Multi-view Learning
• Domain Adaptation for Statistical Classifiers
• Beyond Sharing Weights for Deep Domain Adaptation
• Adversarial Discriminative Domain Adaptation
• Visualizing and Understanding Convolutional Networks
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• Virtual Worlds as Proxy for Multi-Object Tracking Analysis
• Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition
• Playing for Data: Ground Truth from Computer Games
• On Rendering Synthetic Images for Training an Object Detector
• Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
• Deep Transfer Learning with Joint Adaptation Networks
• Generalized Multi-view Embedding for Visual Recognition and Cross-modal Retrieval
• Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
• Webly Supervised Learning of Convolutional Networks
• Domain Generalization for Object Recognition with Multi-task Autoencoders
• A Testbed for Cross-Dataset Analysis
• Learning Attributes Equals Multi-Source Domain Generalization
• Semantic Pose using Deep Networks Trained on Synthetic RGB-D
• Self-Learning Camera: Autonomous Adaptation of Object Detectors to Unlabeled Video Streams
• What is the right way to represent document images?

Cited by in corpus (106)

• Deep Visual Domain Adaptation: A Survey
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• A review of domain adaptation without target labels
• VisDA: The Visual Domain Adaptation Challenge
• Transfer learning for time series classification
• Learning Robust Global Representations by Penalizing Local Predictive Power
• Towards Out-Of-Distribution Generalization: A Survey
• ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection
• A Survey of Domain Adaptation for Neural Machine Translation
• Unsupervised Domain Adaptation through Self-Supervision
• Deep Residual Correction Network for Partial Domain Adaptation
• CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
• Integrating Expert Knowledge with Domain Adaptation for Unsupervised Fault Diagnosis
• Cross-regional oil palm tree counting and detection via multi-level attention domain adaptation network
• MEMO: Test Time Robustness via Adaptation and Augmentation
• Optimal Bayesian Transfer Learning
• Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation
• Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
• Missing-Class-Robust Domain Adaptation by Unilateral Alignment for Fault Diagnosis
• Sample-to-Sample Correspondence for Unsupervised Domain Adaptation
• Unsupervised Person Re-identification by Soft Multilabel Learning
• Small Sample Learning in Big Data Era
• Label Efficient Learning of Transferable Representations across Domains and Tasks
• Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimation
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• Monitoring War Destruction from Space: A Machine Learning Approach
• Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation
• Testing Convolutional Neural Networks for finding strong gravitational lenses in KiDS
• A neural network walks into a lab: towards using deep nets as models for human behavior
• SpotTune: Transfer Learning through Adaptive Fine-tuning
• A Survey on Open Set Recognition
• SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
• Data-Efficient Learning for Sim-to-Real Robotic Grasping using Deep Point Cloud Prediction Networks
• Unsupervised Domain Adaptation in Semantic Segmentation: a Review
• Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation
• GAlaxy Light profile convolutional neural NETworks (GaLNets). I. fast and accurate structural parameters for billion galaxy samples
• Recognition in Terra Incognita
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation
• Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learning
• Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition
• Quickly Inserting Pegs into Uncertain Holes using Multi-view Images and Deep Network Trained on Synthetic Data
• Online Adaptation through Meta-Learning for Stereo Depth Estimation
• Discriminative and Geometry Aware Unsupervised Domain Adaptation
• Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers
• Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation
• Discovering Blind Spots in Reinforcement Learning
• Efficient Deep Neural Networks
• RarePlanes: Synthetic Data Takes Flight
• Self-Supervised Sim-to-Real Adaptation for Visual Robotic Manipulation
• Deep learning for time series classification
• One-Shot Generative Domain Adaptation
• A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes
• Attending to Discriminative Certainty for Domain Adaptation
• HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptation
• Domain adaptation for holistic skin detection
• DINE: Domain Adaptation from Single and Multiple Black-box Predictors
• Concentration bounds for linear Monge mapping estimation and optimal transport domain adaptation
• Hand-Object Contact Consistency Reasoning for Human Grasps Generation
• Model-Based Domain Generalization
• A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation
• Exploiting Local Feature Patterns for Unsupervised Domain Adaptation
• Domain adaptation techniques for improved cross-domain study of galaxy mergers
• Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data
• Implicit 3D Orientation Learning for 6D Object Detection from RGB Images
• Best Practices for Applying Deep Learning to Novel Applications
• An Empirical Study and Analysis on Open-Set Semi-Supervised Learning
• Unsupervised Domain Adaptation for Spatio-Temporal Action Localization
• Large-Scale Historical Watermark Recognition: dataset and a new consistency-based approach
• On Machine Learning and Structure for Mobile Robots
• AdapterNet - learning input transformation for domain adaptation
• Unsupervised Domain Adaptation: from Simulation Engine to the RealWorld
• Joint Semantic Domain Alignment and Target Classifier Learning for Unsupervised Domain Adaptation
• Unsupervised Domain Adaptation using Generative Models and Self-ensembling
• CRAVES: Controlling Robotic Arm with a Vision-based Economic System
• RanLayNet: A Dataset for Document Layout Detection used for Domain Adaptation and Generalization
• Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation
• Safeguarded Dynamic Label Regression for Generalized Noisy Supervision
• Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits
• Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes
• Unsupervised Domain Attention Adaptation Network for Caricature Attribute Recognition
• Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation
• Joint Learning of Neural Networks via Iterative Reweighted Least Squares
• Bearing fault diagnosis based on domain adaptation using transferable features under different working conditions
• Additive Adversarial Learning for Unbiased Authentication
• On the Challenges of Open World Recognitionunder Shifting Visual Domains
• Manifold Criterion Guided Transfer Learning via Intermediate Domain Generation
• DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier
• Classifying Textual Data with Pre-trained Vision Models through Transfer Learning and Data Transformations
• Cross-Domain Image Classification through Neural-Style Transfer Data Augmentation
• Towards Recognizing New Semantic Concepts in New Visual Domains
• Learning Condensed and Aligned Features for Unsupervised Domain Adaptation Using Label Propagation
• Residual-CycleGAN based Camera Adaptation for Robust Diabetic Retinopathy Screening
• Learning joint lesion and tissue segmentation from task-specific hetero-modal datasets
• Cross-domain Adaptation with Discrepancy Minimization for Text-independent Forensic Speaker Verification
• Joint Information Preservation for Heterogeneous Domain Adaptation
• Imitation Learning Approach for AI Driving Olympics Trained on Real-world and Simulation Data Simultaneously
• Unsupervised Domain-Adaptive Person Re-identification Based on Attributes
• When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey
• Visual Domain Adaptation for Monocular Depth Estimation on Resource-Constrained Hardware
• Domain Randomization for Scene-Specific Car Detection and Pose Estimation
• Domain Agnostic Learning for Unbiased Authentication
• Transferable Semantic Augmentation for Domain Adaptation
• Dynamic Adaptation on Non-Stationary Visual Domains
• Transducer Adaptive Ultrasound Volume Reconstruction
• Causality and Generalizability: Identifiability and Learning Methods