MarcellusZhao / awesome-source-free-test-time-adaptation

[2022] A curated list of papers in Test-time Adaptation, Test-time Training and Source-free Domain Adaptation

Awesome Source-free Test-time Adaptation  

This is a curated list of research papers in Test-time Adaptation (TTA), which also goes by other names, such as Test-time Training (TTT), Source-free Domain Adaptation (SFDA) and Unsupervised Model Adaptation (UMA).

The repository is actively maintained. Pull requests or direct messages are welcome.

Table of Contents

• Methods
  • Self-supervision
  • Information Entropy
  • Batch Normalization
  • Pseudo Labeling
  • Class Prototype
  • Feature Alignment
  • Generative Modeling
  • Nearest Neighbors
  • Augmentation Invariance
  • Meta-learning
  • Others
• Applications

Methods

Self-supervision

• Test-Time Training with Self-Supervision for Generalization under Distribution Shifts ICML'20
• TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive? NeurIPS'21
• Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data NeurIPS'21
• Contrastive Test-Time Adaptation CVPR'22

Information Entropy

• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation ICML'20
• Tent: Fully Test-Time Adaptation by Entropy Minimization ICLR'21
• Uncertainty Reduction for Model Adaptation in Semantic Segmentation CVPR'21
• Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation Preprint'21
• Efficient Test-Time Model Adaptation without Forgetting ICML'22
• Confidence Score for Source-Free Unsupervised Domain Adaptation ICML'22

Batch Normalization

• Improving robustness against common corruptions by covariate shift adaptation NeurIPS'20
• Tent: Fully Test-Time Adaptation by Entropy Minimization ICLR'21
• Limitations of Post-Hoc Feature Alignment for Robustness CVPR'21

Pseudo Labeling

• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation ICML'20
• Generative Pseudo-label Refinement for Unsupervised Domain Adaptation WACV'20
• A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data AAAI'21
• Uncertainty Reduction for Model Adaptation in Semantic Segmentation CVPR'21
• Adapting ImageNet-scale models to complex distribution shifts with self-learning Preprint'21
• Continual Test-Time Domain Adaptation CVPR'22
• Contrastive Test-Time Adaptation CVPR'22
• Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Preprint'22

Class Prototype

• Model Adaptation: Unsupervised Domain Adaptation Without Source Data CVPR'20
• Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization NeurIPS'21
• Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Preprint'22

Feature Alignment

• SoFA: Source-data-free Feature Alignment for Unsupervised Domain Adaptation WACV'21
• Adaptive Adversarial Network for Source-Free Domain Adaptation ICCV'21
• TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive? NeurIPS'21
• Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration ICLR'22
• Invariance Through Inference Preprint'21
• Source-Free Domain Adaptation via Distribution Estimation CVPR'22
• Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Preprint'22

Generative Modeling

• Model Adaptation: Unsupervised Domain Adaptation without Source Data CVPR'20
• Domain Impression: A Source Data Free Domain Adaptation Method WACV'21
• Back to the Source: Diffusion-Driven Test-Time Adaptation Preprint'22

Nearest Neighbors

• Generalized Source-free Domain Adaptation ICCV'21
• Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation NeurIPS'21

Augmentation Invariance

• MEMO: Test Time Robustness via Adaptation and Augmentation NeurIPS-WS'21
• Test time Adaptation through Perturbation Robustness NeurIPS-WS'21
• Balancing Discriminability and Transferability for Source-Free Domain Adaptation ICML'22

Meta-learning

• Test-Time Fast Adaptation for Dynamic Scene Deblurring via Meta-Auxiliary Learning CVPR'21
• Adaptive Risk Minimization: Learning to Adapt to Domain Shift NeurIPS'21
• Learning to Generalize across Domains on Single Test Samples ICLR'22

Others

• Domain Adaptation in the Absence of Source Domain Data KDD'16
• Semantic Photo Manipulation with a Generative Image Prior SIGGRAPH'19
• Collaborative Sampling in Generative Adversarial Networks AAAI'20
• Universal Source-Free Domain Adaptation CVPR'20
• Adaptive Methods for Real-World Domain Generalization CVPR'21
• Parameter-free Online Test-time Adaptation CVPR'22

Applications

• Self-Supervised Policy Adaptation during Deployment ICLR'21
• Source-Free Domain Adaptation for Image Segmentation MICCAI'20
• Fully Test-Time Adaptation for Image Segmentation MICCAI'21
• Adapting Off-the-Shelf Source Segmenter for Target Medical Image Segmentation MICCAI'21
• Source-Free Domain Adaptation for Semantic Segmentation CVPR'21
• Generalize Then Adapt: Source-Free Domain Adaptive Semantic Segmentation ICCV'21
• SS-SFDA: Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous Environments ICCV'21
• Test-Time Personalization with a Transformer for Human Pose Estimation NeurIPS'21
• Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective CVPR'22
• Ev-TTA: Test-Time Adaptation for Event-Based Object Recognition CVPR'22
• MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation CVPR'22
• Source-Free Object Detection by Learning to Overlook Domain Style CVPR'22