Locality-aware Private Class Identification for Domain Adaptation with Extreme Label Shift

• URL: http://arxiv.org/abs/2605.05567v1
• Date: Thu, 07 May 2026 01:19:30 GMT
• Title: Locality-aware Private Class Identification for Domain Adaptation with Extreme Label Shift
• Abstract summary: Domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain with different distributions.<n>In real-world scenarios, the label spaces of the two domains often have an inclusion relationship, where some classes exist only in one domain but not the other.<n>Identifying private class samples and mitigating their adverse effects is critical in the literature.
• Score: 25.35870846873358
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain with different distributions. In real-world scenarios, the label spaces of the two domains often have an inclusion relationship, where some classes exist only in one domain but not the other. These non-overlapping classes are referred to as private classes. Identifying private class samples and mitigating their adverse effects is critical in the literature. Existing methods rely on the assumption that shifts in private classes are large enough to be considered outliers. However, the variance within a single shared class can be significantly larger than the difference between a private class and another shared class, challenging this assumption. Consequently, private classes substantially increase the difficulty of cross-domain classification. To address these issues, based on local transportation and metric properties of optimal transport (OT), a locality-aware private class identification approach is proposed in the form of a score function on transport mass. The effectiveness of the proposed approach is theoretically proven, highlighting the score function's strong ability to distinguish between shared and private class samples. Building on this, we introduce a reliable OT-based method (ReOT) for domain adaptation under severe label shift. ReOT minimizes classification risk while learning the separated cluster structure between the identified shared classes and private classes, effectively avoiding mismatch between shared-private sample pairs, thus ensuring that important knowledge is reliably transported intra-class to mitigate class-conditional discrepancy. Furthermore, a generalization upper bound of the target risk is provided for extreme label shift scenarios, which can be minimized by ReOT. Extensive experiments on benchmarks validate the effectiveness of ReOT.

Related papers

• Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios [47.75888552950153]
  Domain generalization learns from multiple source domains to generalize to unseen target domains.<n>Open set domain generalization is then proposed to recognize unseen classes in unseen domains.<n>We propose a novel meta-learning stategy called dualistic MEta-learning with joint DomaIn-Class matching (MEDIC)
  arXiv  Detail & Related papers  (2026-06-22T08:58:08Z)
• Class-based Subset Selection for Transfer Learning under Extreme Label Shift [1.4529850226400594]
  This paper proposes a new process for few-shot transfer learning that selects and weighs classes from the source domain to optimize the transfer between domains.<n>More concretely, we use Wasserstein distance to choose a set of source classes and their weights that minimize the distance between the source and target domain.
  arXiv  Detail & Related papers  (2024-12-30T22:14:24Z)
• Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation [11.875619863954238]
  Partial domain matching (PDM) struggles in extreme cases where many source classes are absent in the target domain.<n>In this work, we identify that the failure of PDM for extreme UniDA stems from dimensional collapse (DC) in target representations.<n>We propose to use the de-collapse techniques in self-supervised learning on the unlabeled target data to preserve the intrinsic structure of the learned representations.
  arXiv  Detail & Related papers  (2024-10-15T04:51:37Z)
• EIANet: A Novel Domain Adaptation Approach to Maximize Class Distinction with Neural Collapse Principles [15.19374752514876]
  Source-free domain adaptation (SFDA) aims to transfer knowledge from a labelled source domain to an unlabelled target domain. A major challenge in SFDA is deriving accurate categorical information for the target domain. We introduce a novel ETF-Informed Attention Network (EIANet) to separate class prototypes.
  arXiv  Detail & Related papers  (2024-07-23T05:31:05Z)
• Exploring Vacant Classes in Label-Skewed Federated Learning [113.65301899666645]
  This paper introduces FedVLS, a novel approach to label-skewed federated learning.<n>It integrates vacant-class distillation and logit suppression simultaneously.<n>Experiments validate the efficacy of FedVLS, demonstrating superior performance compared to previous state-of-the-art (SOTA) methods.
  arXiv  Detail & Related papers  (2024-01-04T16:06:31Z)
• Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization [27.027034515404175]
  We propose a novel framework called dualistic MEta-learning with joint DomaIn-Class matching (MEDIC) Results demonstrate that MEDIC not only outperforms previous methods in open set scenarios, but also maintains competitive close set generalization ability at the same time.
  arXiv  Detail & Related papers  (2023-08-18T08:46:02Z)
• Self-Paced Learning for Open-Set Domain Adaptation [50.620824701934]
  Traditional domain adaptation methods presume that the classes in the source and target domains are identical. Open-set domain adaptation (OSDA) addresses this limitation by allowing previously unseen classes in the target domain. We propose a novel framework based on self-paced learning to distinguish common and unknown class samples.
  arXiv  Detail & Related papers  (2023-03-10T14:11:09Z)
• Unified Optimal Transport Framework for Universal Domain Adaptation [27.860165056943796]
  Universal Domain Adaptation (UniDA) aims to transfer knowledge from a source domain to a target domain without any constraints on label sets. Most existing methods require manually specified or hand-tuned threshold values to detect common samples. We propose to use Optimal Transport (OT) to handle these issues under a unified framework, namely UniOT.
  arXiv  Detail & Related papers  (2022-10-31T05:07:09Z)
• MemSAC: Memory Augmented Sample Consistency for Large Scale Unsupervised Domain Adaptation [71.4942277262067]
  We propose MemSAC, which exploits sample level similarity across source and target domains to achieve discriminative transfer. We provide in-depth analysis and insights into the effectiveness of MemSAC.
  arXiv  Detail & Related papers  (2022-07-25T17:55:28Z)
• From Big to Small: Adaptive Learning to Partial-Set Domains [94.92635970450578]
  Domain adaptation targets at knowledge acquisition and dissemination from a labeled source domain to an unlabeled target domain under distribution shift. Recent advances show that deep pre-trained models of large scale endow rich knowledge to tackle diverse downstream tasks of small scale. This paper introduces Partial Domain Adaptation (PDA), a learning paradigm that relaxes the identical class space assumption to that the source class space subsumes the target class space.
  arXiv  Detail & Related papers  (2022-03-14T07:02:45Z)
• OVANet: One-vs-All Network for Universal Domain Adaptation [78.86047802107025]
  Existing methods manually set a threshold to reject unknown samples based on validation or a pre-defined ratio of unknown samples. We propose a method to learn the threshold using source samples and to adapt it to the target domain. Our idea is that a minimum inter-class distance in the source domain should be a good threshold to decide between known or unknown in the target.
  arXiv  Detail & Related papers  (2021-04-07T18:36:31Z)
• Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation [74.71931918541748]
  We propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA. We first propose a reliable and efficient method to extract similar and dissimilar samples across source and target, and utilize a multi-sample contrastive loss to drive the domain alignment process. We verify the effectiveness of ILA-DA by observing consistent improvements in accuracy over popular domain adaptation approaches on a variety of benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-03T01:33:14Z)
• Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification [64.37745443119942]
  This paper jointly enforces visual and temporal consistency in the combination of a local one-hot classification and a global multi-class classification. Experimental results on three large-scale ReID datasets demonstrate the superiority of proposed method in both unsupervised and unsupervised domain adaptive ReID tasks.
  arXiv  Detail & Related papers  (2020-07-21T14:31:27Z)

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.