Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization

• URL: http://arxiv.org/abs/2308.09391v1
• Date: Fri, 18 Aug 2023 08:46:02 GMT
• Title: Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization
• Abstract summary: 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.
• Score: 27.027034515404175
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Domain generalization (DG) is proposed to deal with the issue of domain shift, which occurs when statistical differences exist between source and target domains. However, most current methods do not account for a common realistic scenario where the source and target domains have different classes. To overcome this deficiency, open set domain generalization (OSDG) then emerges as a more practical setting to recognize unseen classes in unseen domains. An intuitive approach is to use multiple one-vs-all classifiers to define decision boundaries for each class and reject the outliers as unknown. However, the significant class imbalance between positive and negative samples often causes the boundaries biased towards positive ones, resulting in misclassification for known samples in the unseen target domain. In this paper, we propose a novel meta-learning-based framework called dualistic MEta-learning with joint DomaIn-Class matching (MEDIC), which considers gradient matching towards inter-domain and inter-class splits simultaneously to find a generalizable boundary balanced for all tasks. Experimental 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. Our code is available at https://github.com/zzwdx/MEDIC.

Related papers

• Learning Subset-Shared Invariances for Domain Generalization with Mixture-of-Experts [3.893189161468321]
  Domain generalization aims to learn a model from one or more source domains that generalizes to an unseen target domain.<n>A common approach enforces invariance of representations across all source domains, assuming predictive structure is globally shared.<n>We propose subset-shared invariance, where predictive structure is assumed stable only within domain subsets.
  arXiv  Detail & Related papers  (2026-06-24T10:24:57Z)
• 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)
• Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts [56.57141696245328]
  In open-world scenarios, where both novel classes and domains may exist, an ideal segmentation model should detect anomaly classes for safety. Existing methods often struggle to distinguish between domain-level and semantic-level distribution shifts.
  arXiv  Detail & Related papers  (2024-11-06T11:03:02Z)
• 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)
• Towards Adaptive Unknown Authentication for Universal Domain Adaptation by Classifier Paradox [26.411853573816465]
  We propose a new UniDA method with adaptive Unknown Authentication by Paradox (UACP) In UACP, a composite classifier is jointly designed with two types of predictors. That is, a multi-class (MC) predictor classifies samples to one of the multiple source classes, while a binary one-vs-all (OVA) predictor further verifies the prediction by MC predictor. Samples with verification failure or paradox are identified as unknowns. Empirical results validate UACP under both open-set and universal UDA settings.
  arXiv  Detail & Related papers  (2022-07-10T15:58:53Z)
• Domain Generalization via Selective Consistency Regularization for Time Series Classification [16.338176636365752]
  Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains. We propose a novel representation learning methodology that selectively enforces prediction consistency between source domains.
  arXiv  Detail & Related papers  (2022-06-16T01:57:35Z)
• Compound Domain Generalization via Meta-Knowledge Encoding [55.22920476224671]
  We introduce Style-induced Domain-specific Normalization (SDNorm) to re-normalize the multi-modal underlying distributions. We harness the prototype representations, the centroids of classes, to perform relational modeling in the embedding space. Experiments on four standard Domain Generalization benchmarks reveal that COMEN exceeds the state-of-the-art performance without the need of domain supervision.
  arXiv  Detail & Related papers  (2022-03-24T11:54:59Z)
• Discriminative Domain-Invariant Adversarial Network for Deep Domain Generalization [33.84004077585957]
  We propose a discriminative domain-invariant adversarial network (DDIAN) for domain generalization. DDIAN achieves better prediction on unseen target data during training compared to state-of-the-art domain generalization approaches.
  arXiv  Detail & Related papers  (2021-08-20T04:24:12Z)
• Cross-domain Contrastive Learning for Unsupervised Domain Adaptation [108.63914324182984]
  Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. We build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets.
  arXiv  Detail & Related papers  (2021-06-10T06:32:30Z)
• 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)
• Universal Domain Adaptation through Self Supervision [75.04598763659969]
  Unsupervised domain adaptation methods assume that all source categories are present in the target domain. We propose Domain Adaptative Neighborhood Clustering via Entropy optimization (DANCE) to handle arbitrary category shift. We show through extensive experiments that DANCE outperforms baselines across open-set, open-partial and partial domain adaptation settings.
  arXiv  Detail & Related papers  (2020-02-19T01:26:11Z)

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.