Visual Domain Adaptation: A survey of recent advances

2015/04/03 by Vishal M. Patel, Vishal M Patel, Raghuraman Gopalan +2 · 48 citations
Computer Science · Medicine · #Domain Adaptation and Few-Shot Learning #Multimodal Machine Learning Applications #COVID-19 diagnosis using AI

paper · doi:10.1109/msp.2014.2347059

Abstract

In pattern recognition and computer vision, one is often faced with scenarios where the training data used to learn a model have different distribution from the data on which the model is applied. Regardless of the cause, any distributional change that occurs after learning a classifier can degrade its performance at test time. Domain adaptation tries to mitigate this degradation. In this article, we provide a survey of domain adaptation methods for visual recognition. We discuss the merits and drawbacks of existing domain adaptation approaches and identify promising avenues for research in this rapidly evolving field.

Citations

• Sample Selection Bias as a Specification Error

Cited by

• Revisiting Batch Normalization For Practical Domain Adaptation
• Joint cross-domain classification and subspace learning for unsupervised\n adaptation
• Applying Domain Randomization to Synthetic Data for Object Category Detection
• FDA: Fourier Domain Adaptation for Semantic Segmentation
• Predicting Ground-Level Scene Layout from Aerial Imagery
• Nonlinear Invariant Risk Minimization: A Causal Approach
• Summarizing First-Person Videos from Third Persons' Points of Views
• A New PAC-Bayesian Perspective on Domain Adaptation
• Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
• Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching
• Deep Domain Adaptation under Deep Label Scarcity
• Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data
• Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition: A Problem-Oriented Perspective
• Approximate Domain Unlearning for Vision-Language Models
• Time series predictions in unmonitored sites: a survey of machine learning techniques in water resources
• Demystifying Neural Style Transfer
• One-Class Classification: A Survey
• Beyond without Forgetting: Multi-Task Learning for Classification with Disjoint Datasets
• COLA: Context-aware Language-driven Test-time Adaptation
• Hidden Covariate Shift: A Minimal Assumption For Domain Adaptation
• When Unsupervised Domain Adaptation Meets Tensor Representations
• Domain Generalization via Multidomain Discriminant Analysis
• Discriminative Clustering for Robust Unsupervised Domain Adaptation
• Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data
• Biometric Quality: Review and Application to Face Recognition with FaceQnet
• Invariant Feature Learning for Sensor-based Human Activity Recognition
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• Adaptive Visual Navigation Assistant in 3D RPGs
• Neural Style Transfer: A Review
• Discriminative Noise Robust Sparse Orthogonal Label Regression-based Domain Adaptation
• Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds
• In Search of Lost Domain Generalization
• SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
• Domain Agnostic Learning for Unbiased Authentication
• Don't Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights
• Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation
• LRS-DAG: Low Resource Supervised Domain Adaptation with Generalization Across Domains
• SketchParse : Towards Rich Descriptions for Poorly Drawn Sketches using\n Multi-Task Hierarchical Deep Networks
• DORO: Distributional and Outlier Robust Optimization
• Improving Automated Program Repair with Domain Adaptation
• Transport-based analysis, modeling, and learning from signal and data\n distributions
• Towards Universal Object Detection by Domain Attention
• Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation
• DeepRacer: Educational Autonomous Racing Platform for Experimentation with Sim2Real Reinforcement Learning
• Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization
• ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation
• Underwater Monocular Metric Depth Estimation: Real-World Benchmarks and Synthetic Fine-Tuning with Vision Foundation Models
• Recent Advances in Zero-shot Recognition
• Cross-Domain Structure Preserving Projection for Heterogeneous Domain Adaptation

Related

• Domain Adaptations for Computer Vision Applications
• Unsupervised Domain Adaptation with Deep Neural-Network
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Deep Visual Domain Adaptation
• Unsupervised Domain Adaptation: from Simulation Engine to the RealWorld