ICCV2023领域泛化Domain Generalization相关论文

Domain Generalization即领域泛化，是近些年比较前沿的方向之一，顶会论文比较多。

Domain generalization deals with a challenging setting where one or several different but related domain(s) are given, and the goal is to learn a model that can generalize to an unseen test domain.

TKDE2022上有一篇综述论文，可以用于了解该方向的整体情况。

Generalizing to Unseen Domains: A Survey on Domain Generalization

paper链接：https://arxiv.org/abs/2103.03097

以下列出今年ICCV上相关的论文，可用于跟踪前沿研究方向。

1. Cross Contrasting Feature Perturbation for Domain Generalization
2. Domain Generalization via Rationale Invariance
3. Flatness-Aware Minimization for Domain Generalization
4. Texture Learning Domain Randomization for Domain Generalized Segmentation
5. Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters
6. Adversarial Bayesian Augmentation for Single-Source Domain Generalization
7. Activate and Reject: Towards Safe Domain Generalization under Category Shift
8. Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization
9. EV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation
10. A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
11. PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
12. Domain Generalization of 3D Semantic Segmentation in Autonomous Driving
13. Domain Generalization via Balancing Training Difficulty and Model Capability
14. Understanding Hessian Alignment for Domain Generalization
15. DandelionNet: Domain Composition with Instance Adaptive Classification for Domain Generalization
16. DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization
17. iDAG: Invariant DAG Searching for Domain Generalization
18. PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization
19. Towards Unsupervised Domain Generalization for Face Anti-Spoofing