Deep Visual Domain Adaptation: A Survey

Abstract

Deep domain adaption has emerged as a new learning technique to address the lack of massive amounts of labeled data. Compared to conventional methods, which learn shared feature subspaces or reuse important source instances with shallow representations, deep domain adaption methods leverage deep networks to learn more transferable representations by embedding domain adaptation in the pipeline of deep learning. There have been comprehensive surveys for shallow domain adaption, but few timely reviews the emerging deep learning based methods. In this paper, we provide a comprehensive survey of deep domain adaptation methods for computer vision applications with four major contributions. First, we present a taxonomy of different deep domain adaption scenarios according to the properties of data that define how two domains are diverged. Second, we summarize deep domain adaption approaches into several categories based on training loss, and analyze and compare briefly the state-of-the-art methods under these categories. Third, we overview the computer vision applications that go beyond image classification, such as face recognition, semantic segmentation and object detection. Fourth, some potential deficiencies of current methods and several future directions are highlighted.

arXiv commentManuscript accepted by Neurocomputing 2018

References in corpus (54)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Distilling the Knowledge in a Neural Network
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Domain Adaptation by Backpropagation
• Deep Domain Confusion: Maximizing for Domain Invariance
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Generative Adversarial Text to Image Synthesis
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Progressive Neural Networks
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Wasserstein GAN
• Dual Learning for Machine Translation
• Domain Separation Networks
• Learning multiple visual domains with residual adapters
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• Marginalized Denoising Autoencoders for Domain Adaptation
• Beyond Sharing Weights for Deep Domain Adaptation
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• Adversarial Discriminative Domain Adaptation
• Unsupervised Cross-Domain Image Generation
• Revisiting Batch Normalization For Practical Domain Adaptation
• Generative Moment Matching Networks
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Learning with Augmented Features for Heterogeneous Domain Adaptation
• Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
• Few-Shot Adversarial Domain Adaptation
• LSDA: Large Scale Detection Through Adaptation
• Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• Deep Transfer Network: Unsupervised Domain Adaptation
• Deep Transfer Learning with Joint Adaptation Networks
• Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping
• Domain Adaptive Neural Networks for Object Recognition
• Demystifying Neural Style Transfer
• Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation
• One-Shot Adaptation of Supervised Deep Convolutional Models
• Partial Transfer Learning with Selective Adversarial Networks
• Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation
• Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
• Domain Generalization for Object Recognition with Multi-task Autoencoders
• Associative Domain Adaptation
• Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner
• When Unsupervised Domain Adaptation Meets Tensor Representations
• SSPP-DAN: Deep Domain Adaptation Network for Face Recognition with Single Sample Per Person
• Importance Weighted Adversarial Nets for Partial Domain Adaptation
• Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning
• Synthetic to Real Adaptation with Generative Correlation Alignment Networks
• High-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networks
• Fine-to-coarse Knowledge Transfer For Low-Res Image Classification
• Zero-Shot Deep Domain Adaptation

Cited by in corpus (255)

• Shortcut Learning in Deep Neural Networks
• Recent Advances in Open Set Recognition: A Survey
• Deep Face Recognition: A Survey
• Domain Adaptation for Medical Image Analysis: A Survey
• Deep neural network models for computational histopathology: A survey
• A review of domain adaptation without target labels
• Deep Learning for Chest X-ray Analysis: A Survey
• The Emerging Trends of Multi-Label Learning
• Learning Robust Global Representations by Penalizing Local Predictive Power
• A Comprehensive Survey on Transfer Learning
• Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
• Application of Deep Learning in Fundus Image Processing for Ophthalmic Diagnosis -- A Review
• A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networks
• Incorporating Domain Knowledge into Deep Neural Networks
• Unsupervised Domain Adaptation through Self-Supervision
• Self-supervised Domain Adaptation for Computer Vision Tasks
• A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
• Advances in Deep Concealed Scene Understanding
• Improving the generalizability of convolutional neural network-based segmentation on CMR images
• Learning on Attribute-Missing Graphs
• The Role of Cross-Silo Federated Learning in Facilitating Data Sharing in the Agri-Food Sector
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• Deep transfer learning for intrusion detection in industrial control networks: A comprehensive review
• A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects
• Deep Learning Methods For Synthetic Aperture Radar Image Despeckling: An Overview Of Trends And Perspectives
• Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicine
• Synthetic Datasets for Autonomous Driving: A Survey
• Toward Open-World Electroencephalogram Decoding Via Deep Learning: A Comprehensive Survey
• Cross-regional oil palm tree counting and detection via multi-level attention domain adaptation network
• Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification
• From Modern CNNs to Vision Transformers: Assessing the Performance, Robustness, and Classification Strategies of Deep Learning Models in Histopathology
• Deep Learning Based Single Sample Per Person Face Recognition: A Survey
• Visuo-Haptic Object Perception for Robots: An Overview
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• Contrastive Out-of-Distribution Detection for Pretrained Transformers
• A Distance Map Regularized CNN for Cardiac Cine MR Image Segmentation
• Hidden depths in the local Universe: The Stellar Stream Legacy Survey
• FDA: Fourier Domain Adaptation for Semantic Segmentation
• Poisson CNN: Convolutional neural networks for the solution of the Poisson equation on a Cartesian mesh
• Cross-domain Activity Recognition via Substructural Optimal Transport
• IDDA: a large-scale multi-domain dataset for autonomous driving
• Continuous Human Action Recognition for Human-Machine Interaction: A Review
• Deep Prototypical Networks Based Domain Adaptation for Fault Diagnosis
• OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
• SAN-Net: Learning Generalization to Unseen Sites for Stroke Lesion Segmentation with Self-Adaptive Normalization
• Unsupervised Structure-Texture Separation Network for Oracle Character Recognition
• A Sentinel-2 multi-year, multi-country benchmark dataset for crop classification and segmentation with deep learning
• Embrace Limited and Imperfect Training Datasets: Opportunities and Challenges in Plant Disease Recognition Using Deep Learning
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• DeepMerge II: Building Robust Deep Learning Algorithms for Merging Galaxy Identification Across Domains
• Deep Learning based HEp-2 Image Classification: A Comprehensive Review
• Image Classification with Small Datasets: Overview and Benchmark
• Learning Target Domain Specific Classifier for Partial Domain Adaptation
• Self-Challenging Improves Cross-Domain Generalization
• Fine-tuning deep learning model parameters for improved super-resolution of dynamic MRI with prior-knowledge
• DAICS: A Deep Learning Solution for Anomaly Detection in Industrial Control Systems
• Deep Transparent Prediction through Latent Representation Analysis
• The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions
• Virtual to Real adaptation of Pedestrian Detectors
• Racial Faces in-the-Wild: Reducing Racial Bias by Information Maximization Adaptation Network
• Anatomy-aware and acquisition-agnostic joint registration with SynthMorph
• Unsupervised domain adaptation based COVID-19 CT infection segmentation network
• Image segmentation for analyzing galaxy-galaxy strong lensing systems
• A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques
• Adaptive Filters in Graph Convolutional Neural Networks
• Unsupervised Domain Adaptation in Semantic Segmentation: a Review
• Towards out of distribution generalization for problems in mechanics
• Photoacoustic image synthesis with generative adversarial networks
• TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation
• Evolutionary Multitask Optimization: Fundamental Research Questions, Practices, and Directions for the Future
• A review of Recent Techniques for Person Re-Identification
• Unsupervised Neural Domain Adaptation for Document Image Binarization
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• Deep Learning for Scene Classification: A Survey
• Multi-Source EEG Emotion Recognition via Dynamic Contrastive Domain Adaptation
• Synthetic Elastography using B-mode Ultrasound through a Deep Fully-Convolutional Neural Network
• Learning to Discover Novel Visual Categories via Deep Transfer Clustering
• RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation
• Towards Shape Biased Unsupervised Representation Learning for Domain Generalization
• Modality Attention and Sampling Enables Deep Learning with Heterogeneous Marker Combinations in Fluorescence Microscopy
• PAC-Bayes and Domain Adaptation
• A Survey on Self-supervised Pre-training for Sequential Transfer Learning in Neural Networks
• All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes
• Exploiting Natural Language for Efficient Risk-Aware Multi-robot SaR Planning
• SceneFlowFields++: Multi-frame Matching, Visibility Prediction, and Robust Interpolation for Scene Flow Estimation
• Self-training for Few-shot Transfer Across Extreme Task Differences
• Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error
• Active Learning for Deep Detection Neural Networks
• Deep neural networks for choice analysis: Enhancing behavioral regularity with gradient regularization
• Unsupervised Domain Adaptation from Axial to Short-Axis Multi-Slice Cardiac MR Images by Incorporating Pretrained Task Networks
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• To Tune or Not To Tune? How About the Best of Both Worlds?
• Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey
• Realistic galaxy images and improved robustness in machine learning tasks from generative modelling
• Anatomy-guided domain adaptation for 3D in-bed human pose estimation
• A Comprehensive Approach for UAV Small Object Detection with Simulation-based Transfer Learning and Adaptive Fusion
• Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
• Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners
• Synthetic-to-Real Domain Adaptation using Contrastive Unpaired Translation
• DIGS: Deep Inference of Galaxy Spectra with Neural Posterior Estimation
• PixelVAE++: Improved PixelVAE with Discrete Prior
• The Cells Out of Sample (COOS) dataset and benchmarks for measuring out-of-sample generalization of image classifiers
• MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption
• Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks
• Domain adaptation under structural causal models
• Distributed Learning and Inference with Compressed Images
• Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization
• Deep Domain Adaptive Object Detection: a Survey
• Surgical Visual Domain Adaptation: Results from the MICCAI 2020 SurgVisDom Challenge
• Domain-knowledge Inspired Pseudo Supervision (DIPS) for Unsupervised Image-to-Image Translation Models to Support Cross-Domain Classification
• DiversityOne: A Multi-Country Smartphone Sensor Dataset for Everyday Life Behavior Modeling
• Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models
• Entity Linking Meets Deep Learning: Techniques and Solutions
• Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning
• Deep learning in automated ultrasonic NDE -- developments, axioms and opportunities
• A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds
• Speaker Recognition Based on Deep Learning: An Overview
• Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition
• OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• Improving Compound Activity Classification via Deep Transfer and Representation Learning
• SatImNet: Structured and Harmonised Training Data for Enhanced Satellite Imagery Classification
• DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classification
• DAMIA: Leveraging Domain Adaptation as a Defense against Membership Inference Attacks
• Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
• Learning to Switch CNNs with Model Agnostic Meta Learning for Fine Precision Visual Servoing
• Attending to Discriminative Certainty for Domain Adaptation
• Optimizing Image Capture for Computer Vision-Powered Taxonomic Identification and Trait Recognition of Biodiversity Specimens
• Data Augmentation with norm-VAE for Unsupervised Domain Adaptation
• Class-imbalanced Domain Adaptation: An Empirical Odyssey
• Deep causal representation learning for unsupervised domain adaptation
• Transfer Learning Study of Motion Transformer-based Trajectory Predictions
• Multi-layer Representation Learning for Robust OOD Image Classification
• Modeling of a Liquid Leaf Target TNSA Experiment using Particle-In-Cell Simulations and Deep Learning
• Combining Self-Supervised and Supervised Learning with Noisy Labels
• An Adversarial Domain Separation Framework for Septic Shock Early Prediction Across EHR Systems
• Co-training for On-board Deep Object Detection
• Understanding Continual Learning Settings with Data Distribution Drift Analysis
• Analyzing domain shift when using additional data for the MICCAI KiTS23 Challenge
• Unsupervised Domain Adaptation via Disentangled Representations: Application to Cross-Modality Liver Segmentation
• Federated Action Recognition on Heterogeneous Embedded Devices
• Towards Backward-Compatible Representation Learning
• Domain adaptation techniques for improved cross-domain study of galaxy mergers
• Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark
• Domain Adapting Ability of Self-Supervised Learning for Face Recognition
• AdapterNet - learning input transformation for domain adaptation
• Training on Test Data with Bayesian Adaptation for Covariate Shift
• Self-Supervised Object-in-Gripper Segmentation from Robotic Motions
• An Empirical Study and Analysis on Open-Set Semi-Supervised Learning
• Semi-Supervised Transfer Boosting (SS-TrBoosting)
• Style Feature Extraction Using Contrastive Conditioned Variational Autoencoders with Mutual Information Constraints
• Applications of Deep Learning in Fundus Images: A Review
• Adversarial Graph Representation Adaptation for Cross-Domain Facial Expression Recognition
• Perceptual-assisted Adversarial Adaptation for Choroid Segmentation in optical coherence tomography
• Learning to Diversify for Single Domain Generalization
• Deeply Aligned Adaptation for Cross-domain Object Detection
• Unsupervised Domain Adaptation with Progressive Domain Augmentation
• SB-MTL: Score-based Meta Transfer-Learning for Cross-Domain Few-Shot Learning
• Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits
• Mitigating Uncertainty of Classifier for Unsupervised Domain Adaptation
• Domain Adaptation for Sentiment Analysis Using Increased Intraclass Separation
• Predicting with High Correlation Features
• Supervised Domain Adaptation using Graph Embedding
• Using Latent Codes for Class Imbalance Problem in Unsupervised Domain Adaptation
• Uncertainty-Aware Model Adaptation for Unsupervised Cross-Domain Object Detection
• Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation
• CNN Feature Map Augmentation for Single-Source Domain Generalization
• Robust and Communication-Efficient Federated Domain Adaptation via Random Features
• Unified Representation Learning for Cross Model Compatibility
• Box Re-Ranking: Unsupervised False Positive Suppression for Domain Adaptive Pedestrian Detection
• An Information-theoretic Approach to Distribution Shifts
• Dynamic Feature Alignment for Semi-supervised Domain Adaptation
• Domain-randomized deep learning for neuroimage analysis
• Structural Regularization
• CADA: Multi-scale Collaborative Adversarial Domain Adaptation for Unsupervised Optic Disc and Cup Segmentation
• Multi-Source Deep Domain Adaptation for Quality Control in Retail Food Packaging
• Deep Optimal Transport for Domain Adaptation on SPD Manifolds
• MAX: Masked Autoencoder for X-ray Fluorescence in Geological Investigation
• Incremental Unsupervised Domain-Adversarial Training of Neural Networks
• Discriminative Active Learning for Domain Adaptation
• FedCTTA: A Collaborative Approach to Continual Test-Time Adaptation in Federated Learning
• Additive Adversarial Learning for Unbiased Authentication
• Ubiquitous Acoustic Sensing on Commodity IoT Devices: A Survey
• Smart Home Appliances: Chat with Your Fridge
• Generative Self-training for Cross-domain Unsupervised Tagged-to-Cine MRI Synthesis
• Self-Adaptive Transfer Learning for Multicenter Glaucoma Classification in Fundus Retina Images
• Joint Semi-supervised 3D Super-Resolution and Segmentation with Mixed Adversarial Gaussian Domain Adaptation
• Domain-Adversarial Training of Self-Attention Based Networks for Land Cover Classification using Multi-temporal Sentinel-2 Satellite Imagery
• Multilevel Knowledge Transfer for Cross-Domain Object Detection
• A Bayesian Approach to (Online) Transfer Learning: Theory and Algorithms
• Sim-to-Real Transfer via a Style-Identified Cycle Consistent Generative Adversarial Network: Zero-Shot Deployment on Robotic Manipulators through Visual Domain Adaptation
• Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation
• Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentation
• Exploring Bottom-up and Top-down Cues with Attentive Learning for Webly Supervised Object Detection
• Time Series Analysis of Urban Liveability
• Not Only Domain Randomization: Universal Policy with Embedding System Identification
• Improving the Generalization of Meta-learning on Unseen Domains via Adversarial Shift
• REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter
• Instance-Level Safety-Aware Fidelity of Synthetic Data and Its Calibration
• Heterogeneous Domain Adaptation with Positive and Unlabeled Data
• Unsupervised Domain Adaptation Network with Category-Centric Prototype Aligner for Biomedical Image Segmentation
• Adapting Convolutional Neural Networks for Geographical Domain Shift
• Deep Generative Model with Beta Bernoulli Process for Modeling and Learning Confounding Factors
• Fashion CUT: Unsupervised domain adaptation for visual pattern classification in clothes using synthetic data and pseudo-labels
• Towards Recognizing New Semantic Concepts in New Visual Domains
• Towards Robust Pattern Recognition: A Review
• Self-Supervised Dynamic Networks for Covariate Shift Robustness
• Matching Embeddings for Domain Adaptation
• Semi-Supervised Adversarial Discriminative Domain Adaptation
• TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognition
• Liver Segmentation using Turbolift Learning for CT and Cone-beam C-arm Perfusion Imaging
• AdaVocoder: Adaptive Vocoder for Custom Voice
• Which Augmentation Should I Use? An Empirical Investigation of Augmentations for Self-Supervised Phonocardiogram Representation Learning
• Materials In Paintings (MIP): An interdisciplinary dataset for perception, art history, and computer vision
• Deep DA for Ordinal Regression of Pain Intensity Estimation Using Weakly-Labeled Videos
• Covariate shift in nonparametric regression with Markovian design
• The TYC Dataset for Understanding Instance-Level Semantics and Motions of Cells in Microstructures
• Development of Hybrid Artificial Intelligence Training on Real and Synthetic Data: Benchmark on Two Mixed Training Strategies
• Should All Noises Be Treated Equally: Impact of Input Noise Variability on Neural Network Robustness
• Heterogeneous Model Fusion for Privacy-Aware Multi-Camera Surveillance via Synthetic Domain Adaptation
• Unsupervised Domain Adaptation for Multitask Image Analysis in Realistic Context with Extreme Label Shift; Application to the CTAO first Large Sized Telescope
• Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization
• Deep Domain Adaptation for Pavement Crack Detection
• Towards Data-Free Domain Generalization
• Unsupervised Local Discrimination for Medical Images
• Achieving Domain Robustness in Stereo Matching Networks by Removing Shortcut Learning
• Disentangling Transfer and Interference in Multi-Domain Learning
• Leveraging semantically similar queries for ranking via combining representations
• ADeLA: Automatic Dense Labeling with Attention for Viewpoint Adaptation in Semantic Segmentation
• Multi-Object Tracking with Hallucinated and Unlabeled Videos
• Generating Annotated Training Data for 6D Object Pose Estimation in Operational Environments with Minimal User Interaction
• Domain Adaptation and Active Learning for Fine-Grained Recognition in the Field of Biodiversity
• Domain Adaptation for Rare Classes Augmented with Synthetic Samples
• Neural Random Projection: From the Initial Task To the Input Similarity Problem
• Localising In Complex Scenes Using Balanced Adversarial Adaptation
• Causal Transfer Random Forest: Combining Logged Data and Randomized Experiments for Robust Prediction
• Domain Agnostic Learning for Unbiased Authentication
• Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering
• R-AGNO-RPN: A LIDAR-Camera Region Deep Network for Resolution-Agnostic Detection
• Restyling Images with the Bangladeshi Paintings Using Neural Style Transfer: A Comprehensive Experiment, Evaluation, and Human Perspective
• Unsupervised Domain Adaptation Through Transferring both the Source-Knowledge and Target-Relatedness Simultaneously
• Towards Fair Cross-Domain Adaptation via Generative Learning
• Learning Deep Features for Shape Correspondence with Domain Invariance
• A Batch Normalization Classifier for Domain Adaptation
• Semi-Supervised Domain Adaptation via Selective Pseudo Labeling and Progressive Self-Training
• Domain-Agnostic Learning with Anatomy-Consistent Embedding for Cross-Modality Liver Segmentation
• A Simple Domain Shifting Networkfor Generating Low Quality Images
• Residual-CycleGAN based Camera Adaptation for Robust Diabetic Retinopathy Screening
• Adversarial Domain Randomization
• Syn2Real: Forgery Classification via Unsupervised Domain Adaptation
• A neural network model of perception and reasoning
• Domain Randomization for Scene-Specific Car Detection and Pose Estimation
• Transfer Representation Learning with TSK Fuzzy System
• Deep Domain Adaptation under Deep Label Scarcity
• Dynamic Adaptation on Non-Stationary Visual Domains