Towards Context-Aware Domain Generalization: Understanding the Benefits and Limits of Marginal Transfer Learning
원문 초록
In this work, we analyze the conditions under which information about the context of an input $X$ can improve the predictions of deep learning models in new domains. Following work in marginal transfer learning in Domain Generalization (DG), we formalize the notion of context as a permutation-invariant representation of a set of data points that originate from the same domain as the input itself. We offer a theoretical analysis of the conditions under which this approach can, in principle, yield benefits, and formulate two necessary criteria that can be easily verified in practice. Additionally, we contribute insights into the kind of distribution shifts for which the marginal transfer learning approach promises robustness. Empirical analysis shows that our criteria are effective in discerning both favorable and unfavorable scenarios. Finally, we demonstrate that we can reliably detect scenarios where a model is tasked with unwarranted extrapolation in out-of-distribution (OOD) domains, identifying potential failure cases. Consequently, we showcase a method to select between the most predictive and the most robust model, circumventing the well-known trade-off between predictive performance and robustness.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains
Towards A Generalist Code Embedding Model Based On Massive Data Synthesis
Rethinking the Role of Operating Conditions for Learning-based Multi-condition Fault Diagnosis
Geometrically Regularized Transfer Learning with On-Manifold and Off-Manifold Perturbation
On the Mechanisms of Adversarial Data Augmentation for Robust and Adaptive Transfer Learning
CLIP-aware Domain-Adaptive Super-Resolution
토론
이 논문과 연결된 포럼 글이 아직 없습니다.