ICCV23中的域泛化相关研究
- 【OCR】Order-preserving Consistency Regularization for Domain Adaptation and Generalization
- 【iDAG】iDAG: Invariant DAG Searching for Domain Generalization
- 【RIDG】Domain Generalization via Rationale Invariance
- 【3DLabelProp】Domain Generalization of 3D Semantic Segmentation in Autonomous Driving
- 【MoDify】Domain Generalization via Balancing Training Difficulty and Model Capability
- 【DandelionNet】DandelionNet: Domain Composition with Instance Adaptive Classification for Domain Generalization
- 【PASTA】PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization
- 【PromptStyler】PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
- Towards Unsupervised Domain Generalization for Face Anti-Spoofing
- 【ABA】Adversarial Bayesian Augmentation for Single-Source Domain Generalization
- 【CoDAG】Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learning
- BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation
- Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning
- 【SHIP】Improving Zero-Shot Generalization for CLIP with Synthesized Prompts
- MAP: Towards Balanced Generalization of IID and OOD through Model-Agnostic Adapters
- Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization
- Flatness-Aware Minimization for Domain Generalization
- Understanding Hessian Alignment for Domain Generalization
- Bayesian Prompt Learning for Image-Language Model Generalization
- Global Adaptation Meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation
- Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation
- Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization
- Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation
- Activate and Reject: Towards Safe Domain Generalization under Category Shift
- A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
- Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters
- Cross Contrasting Feature Perturbation for Domain Generalization
- DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization
【OCR】Order-preserving Consistency Regularization for Domain Adaptation and Generalization
- 论文链接
- 提出保持分类概率的顺序一致性，这可能适用于所有一致性约束的方法
【iDAG】iDAG: Invariant DAG Searching for Domain Generalization
- 论文链接
- https://github.com/lccurious/iDAG
【RIDG】Domain Generalization via Rationale Invariance
- 论文链接
- https://github.com/liangchen527/RIDG
【3DLabelProp】Domain Generalization of 3D Semantic Segmentation in Autonomous Driving
- 论文链接
- https://github.com/JulesSanchez/3DLabelProp
- 提出了第一个用于无人驾驶场景的3D语义分割域泛化benchmark和方法
【MoDify】Domain Generalization via Balancing Training Difficulty and Model Capability
- 论文链接
- 大多数现有工作都存在训练样本的难度级别与当代训练模型的能力之间的不一致，导致训练泛化模型中的过度拟合或拟合不足。本文提出在学习时平衡模型能力和样本难度之间的“跷跷板”。该方法是通用的，可以用于不同的视觉识别任务。
【DandelionNet】DandelionNet: Domain Composition with Instance Adaptive Classification for Domain Generalization
- 论文链接
- 本文认为多个域在特征空间中不应该紧密对齐，而是应该组合在一起，所有域都靠拢，但仍然分别保留其个性 (we propose that the multiple domains should not be tightly aligned but composite together, where all domains are pulled closer but still preserve their individuality respectively.)，就像蒲公英一样。这是通过instance-adaptive分类器实现的，它允许来自同一类别但不同域的所有实例分散在类中心周围，而不是紧紧挤压，从而更好地泛化到看不见的域样本
【PASTA】PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization
- 论文链接
- https://github.com/prithv1/PASTA
- 频域增强提升域泛化的性能
【PromptStyler】PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
- 论文链接
- https://promptstyler.github.io/
- 用prompt学习风格特征，不需要图像参与训练
Towards Unsupervised Domain Generalization for Face Anti-Spoofing
- 论文链接
【ABA】Adversarial Bayesian Augmentation for Single-Source Domain Generalization
- 论文链接
- https://github.com/shengcheng/ABA
【CoDAG】Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learning
- 论文链接
BEV-DG: Cross-Modal Learning under Bird’s-Eye View for Domain Generalization of 3D Semantic Segmentation
- 论文链接
Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning
- 论文链接
【SHIP】Improving Zero-Shot Generalization for CLIP with Synthesized Prompts
- 论文链接
- https://github.com/mrflogs/SHIP
MAP: Towards Balanced Generalization of IID and OOD through Model-Agnostic Adapters
- 论文链接
Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization
- 论文链接
Flatness-Aware Minimization for Domain Generalization
- 论文链接
Understanding Hessian Alignment for Domain Generalization
- 论文链接
Bayesian Prompt Learning for Image-Language Model Generalization
- 论文链接
- https://github.com/saic-fi/Bayesian-Prompt-Learning
Global Adaptation Meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation
- 论文链接
Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation
- 论文链接
Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization
- 论文链接
Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation
- 论文链接
Activate and Reject: Towards Safe Domain Generalization under Category Shift
- 论文链接
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
- 论文链接
Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters
- 论文链接
Cross Contrasting Feature Perturbation for Domain Generalization
- 论文链接
DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization
- 论文链接
![skywalking动态配置[集成nacos/apollo/consul]](https://img-blog.csdnimg.cn/fa78c3d555b44bd9b4e28f07c562cc9a.png)
