DomainBed
PulseAugur coverage of DomainBed — every cluster mentioning DomainBed across labs, papers, and developer communities, ranked by signal.
-
UniF-MoE framework unifies adaptive MoE computation for improved efficiency
Researchers have introduced UniF-MoE, a novel framework for Mixture-of-Experts (MoE) computation that unifies various adaptive strategies. This approach decomposes experts into blocks, allowing for shared computation fi…
-
New SAGE method improves multi-distribution learning by considering flatness and gradient alignment
Researchers have introduced SAGE (Spectral-Aware Gradient-Aligned Exploration), a novel method for multi-distribution learning that addresses limitations in existing approaches. Unlike methods that focus solely on flatn…
-
New method learns domain generalization via subset-shared invariances
Researchers have introduced a new approach to domain generalization called subset-shared invariance, which addresses limitations of current methods that enforce global invariance across all source domains. This new tech…
-
New SAGE method improves multi-distribution learning by considering flatness and gradient alignment
Researchers have introduced a new method called SAGE (Spectral-Aware Gradient-Aligned Exploration) that addresses limitations in existing generalization techniques for multi-distribution learning. Unlike prior methods t…
-
New PARSE framework enhances domain generalization in image classification
Researchers have developed a new framework called PARSE (Primitive-Aware Relational Structure for domain gEneralization) to improve image classification across different domains. This method breaks down visual recogniti…
-
New FGMix method improves domain generalization by learning mixup policies
Researchers have developed a new domain generalization technique called Flatness-aware Gradient-based Mixup (FGMix). This method uses data interpolation and extrapolation to improve model generalization by covering a wi…