On the Transferability and Discriminability of Repersentation Learning in Unsupervised Domain Adaptation

• URL: http://arxiv.org/abs/2505.22099v1
• Date: Wed, 28 May 2025 08:24:43 GMT
• Title: On the Transferability and Discriminability of Repersentation Learning in Unsupervised Domain Adaptation
• Authors: Wenwen Qiang, Ziyin Gu, Lingyu Si, Jiangmeng Li, Changwen Zheng, Fuchun Sun, Hui Xiong,
• Abstract summary: A standard adversarial-based framework neglects the discriminability of target-domain features, leading to suboptimal performance.<n>We propose a novel framework that explicitly integrates a domain alignment objective with a discriminability-enhancing constraint.
• Score: 40.32838937328407
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we addressed the limitation of relying solely on distribution alignment and source-domain empirical risk minimization in Unsupervised Domain Adaptation (UDA). Our information-theoretic analysis showed that this standard adversarial-based framework neglects the discriminability of target-domain features, leading to suboptimal performance. To bridge this theoretical-practical gap, we defined "good representation learning" as guaranteeing both transferability and discriminability, and proved that an additional loss term targeting target-domain discriminability is necessary. Building on these insights, we proposed a novel adversarial-based UDA framework that explicitly integrates a domain alignment objective with a discriminability-enhancing constraint. Instantiated as Domain-Invariant Representation Learning with Global and Local Consistency (RLGLC), our method leverages Asymmetrically-Relaxed Wasserstein of Wasserstein Distance (AR-WWD) to address class imbalance and semantic dimension weighting, and employs a local consistency mechanism to preserve fine-grained target-domain discriminative information. Extensive experiments across multiple benchmark datasets demonstrate that RLGLC consistently surpasses state-of-the-art methods, confirming the value of our theoretical perspective and underscoring the necessity of enforcing both transferability and discriminability in adversarial-based UDA.

Related papers

• Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment [87.8301166955305]
  We propose a novel bi-discriminator domain adversarial neural network with class-level gradient alignment. BACG resorts to gradient signals and second-order probability estimation for better alignment of domain distributions. In addition, inspired by contrastive learning, we develop a memory bank-based variant, i.e. Fast-BACG, which can greatly shorten the training process.
  arXiv  Detail & Related papers  (2023-10-21T09:53:17Z)
• CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift [9.2929174544214]
  Unsupervised domain adaptation (UDA) refers to a domain adaptation framework in which a learning model is trained based on the labeled samples on the source domain and unlabeled ones in the target domain.<n>We propose a novel Conditional Adversarial SUpport ALignment (CASUAL) whose aim is to minimize the conditional symmetric support divergence between the source's and target domain's feature representation distributions.
  arXiv  Detail & Related papers  (2023-05-29T05:20:18Z)
• Balancing Discriminability and Transferability for Source-Free Domain Adaptation [55.143687986324935]
  Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations. The requirement of simultaneous access to labeled source and unlabeled target renders them unsuitable for the challenging source-free DA setting. We derive novel insights to show that a mixup between original and corresponding translated generic samples enhances the discriminability-transferability trade-off.
  arXiv  Detail & Related papers  (2022-06-16T09:06:22Z)
• Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling [107.24387363079629]
  Domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled or a less labeled but related target domain. Due to the imbalance between the amount of annotated data in the source and target domains, only the target distribution is aligned to the source domain. We propose a non-intrusive Unbiased Transferability Estimation Plug-in (UTEP) by modeling the uncertainty of a discriminator in adversarial-based DA methods to optimize unbiased transfer.
  arXiv  Detail & Related papers  (2022-06-02T21:58:54Z)
• Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation [24.9073164947711]
  We present Bi-Classifier Determinacy Maximization(BCDM) to tackle this problem. Motivated by the observation that target samples cannot always be separated distinctly by the decision boundary, we design a novel classifier determinacy disparity metric. BCDM can generate discriminative representations by encouraging target predictive outputs to be consistent and determined.
  arXiv  Detail & Related papers  (2020-12-13T07:55:39Z)
• Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation [61.317911756566126]
  We propose a Towards Fair Knowledge Transfer framework to handle the fairness challenge in imbalanced cross-domain learning. Specifically, a novel cross-domain mixup generation is exploited to augment the minority source set with target information to enhance fairness. Our model significantly improves over 20% on two benchmarks in terms of the overall accuracy.
  arXiv  Detail & Related papers  (2020-10-23T06:29:09Z)
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation [109.73983088432364]
  We propose the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA) We introduce the LIRR algorithm for jointly textbfLearning textbfInvariant textbfRepresentations and textbfRisks.
  arXiv  Detail & Related papers  (2020-10-09T15:42:35Z)
• Learning transferable and discriminative features for unsupervised domain adaptation [6.37626180021317]
  Unsupervised domain adaptation is able to overcome this challenge by transferring knowledge from a labeled source domain to an unlabeled target domain. In this paper, a novel method called textitlearning TransFerable and Discriminative Features for unsupervised domain adaptation (TLearning) is proposed to optimize these two objectives simultaneously. Comprehensive experiments are conducted on five real-world datasets and the results verify the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2020-03-26T03:15:09Z)
• Unsupervised Domain Adaptation via Discriminative Manifold Embedding and Alignment [23.72562139715191]
  Unsupervised domain adaptation is effective in leveraging the rich information from the source domain to the unsupervised target domain. The hard-assigned pseudo labels on the target domain are risky to the intrinsic data structure. A consistent manifold learning framework is proposed to achieve transferability and discriminability consistently.
  arXiv  Detail & Related papers  (2020-02-20T11:06:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.