提出新方法提升跨域迁移中的几何对齐精度与鲁棒性
Disentangled Geometric Alignment with Adaptive Contrastive Perturbation for Reliable Domain Transfer
- 分离潜在空间中与任务相关和无关的特征维度
- 根据类别差异自适应调整扰动策略，提升对齐精度
- 适合关注跨域迁移中语义几何对齐的研究者
尽管几何感知域自适应取得进展，现有方法如 GAMA 仍存在两个未解问题：(1) 任务相关与无关流形维度分离不足；(2) 扰动策略僵化，忽略类别间对齐不对称性。为此，我们提出 GAMA++，引入 (i) 潜在空间解耦以分离标签一致的流形方向与干扰因素，(ii) 自适应对比扰动策略，针对类别特定的流形曲率与对齐差异调整在线与离线探索。此外，提出跨域对比一致性损失，促进局部语义簇对齐同时保持域内多样性。该方法在 DomainNet、Office-Home 与 VisDA 基准上实现最优性能，尤其在类别级对齐保真度与边界鲁棒性方面显著提升。GAMA++ 为迁移学习中的语义几何对齐树立了新标准。
原文摘要 · Abstract (English)
Despite progress in geometry-aware domain adaptation, current methods such as GAMA still suffer from two unresolved issues: (1) insufficient disentanglement of task-relevant and task-irrelevant manifold dimensions, and (2) rigid perturbation schemes that ignore per-class alignment asymmetries. To address this, we propose GAMA++, a novel framework that introduces (i) latent space disentanglement to isolate label-consistent manifold directions from nuisance factors, and (ii) an adaptive contrastive perturbation strategy that tailors both on- and off-manifold exploration to class-specific manifold curvature and alignment discrepancy. We further propose a cross-domain contrastive consistency loss that encourages local semantic clusters to align while preserving intra-domain diversity. Our method achieves state-of-the-art results on DomainNet, Office-Home, and VisDA benchmarks under both standard and few-shot settings, with notable improvements in class-level alignment fidelity and boundary robustness. GAMA++ sets a new standard for semantic geometry alignment in transfer learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。