# Manifold Criterion Guided Transfer Learning via Intermediate Domain Generation

arXiv: https://arxiv.org/abs/1903.10211 · HTML: https://mlsanity.com/paper/1903.10211/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Mar 2019.

## Built on by (most cited first, 7 of 7)

- [Contrastive Domain Adaptation for Time-Series via Temporal Mixup](https://mlsanity.com/paper/2212.01555/) (2022)
- [Attention Regularized Laplace Graph for Domain Adaptation](https://mlsanity.com/paper/2210.08170/) (2022)
- [Beyond Batch Learning: Global Awareness Enhanced Domain Adaptation](https://mlsanity.com/paper/2502.06272/) (2025)
- [E-ADDA: Unsupervised Adversarial Domain Adaptation Enhanced by a New Mahalanobis Distance Loss for Smart Computing](https://mlsanity.com/paper/2201.10001/) (2022)
- [Envelope imbalanced ensemble model with deep sample learning and local-global structure consistency](https://mlsanity.com/paper/2206.13507/) (2022)
- [Gradually Vanishing Gap in Prototypical Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2405.17774/) (2024)
- [Two stages domain invariant representation learners solve the large co-variate shift in unsupervised domain adaptation with two dimensional data domains](https://mlsanity.com/paper/2412.04682/) (2024)

## Abstract (arXiv)

In many practical transfer learning scenarios, the feature distribution is different across the source and target domains (i.e. non-i.i.d.). Maximum mean discrepancy (MMD), as a domain discrepancy metric, has achieved promising performance in unsupervised domain adaptation (DA). We argue that MMD-based DA methods ignore the data locality structure, which, to some extent, would cause the negative transfer effect. The locality plays an important role in minimizing the nonlinear local domain discrepancy underlying the marginal distributions. For better exploiting the domain locality, a novel local generative discrepancy metric (LGDM) based intermediate domain generation learning called Manifold Criterion guided Transfer Learning (MCTL) is proposed in this paper. The merits of the proposed MCTL are four-fold: 1) the concept of manifold criterion (MC) is first proposed as a measure validating the distribution matching across domains, and domain adaptation is achieved if the MC is satisfied; 2) the proposed MC can well guide the generation of the intermediate domain sharing similar distribution with the target domain, by minimizing the local domain discrepancy; 3) a global generative discrepancy metric (GGDM) is presented, such that both the global and local discrepancy can be effectively and positively reduced; 4) a simplified version of MCTL called MCTL-S is presented under a perfect domain generation assumption for more generic learning scenario. Experiments on a number of benchmark visual transfer tasks demonstrate the superiority of the proposed manifold criterion guided generative transfer method, by comparing with other state-of-the-art methods. The source code is available in https://github.com/wangshanshanCQU/MCTL.