Prototypical Partial Optimal Transport for Universal Domain Adaptation

• URL: http://arxiv.org/abs/2408.01089v1
• Date: Fri, 2 Aug 2024 08:08:56 GMT
• Title: Prototypical Partial Optimal Transport for Universal Domain Adaptation
• Authors: Yucheng Yang, Xiang Gu, Jian Sun,
• Abstract summary: Universal domain adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. The existence of domain and category shift makes the task challenging and requires us to distinguish "known" samples and "unknown" samples. A novel approach, dubbed mini-batch Prototypical Partial Optimal Transport (m-PPOT), is proposed to conduct partial distribution alignment for UniDA.
• Score: 48.07871397146472
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Universal domain adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain without requiring the same label sets of both domains. The existence of domain and category shift makes the task challenging and requires us to distinguish "known" samples (i.e., samples whose labels exist in both domains) and "unknown" samples (i.e., samples whose labels exist in only one domain) in both domains before reducing the domain gap. In this paper, we consider the problem from the point of view of distribution matching which we only need to align two distributions partially. A novel approach, dubbed mini-batch Prototypical Partial Optimal Transport (m-PPOT), is proposed to conduct partial distribution alignment for UniDA. In training phase, besides minimizing m-PPOT, we also leverage the transport plan of m-PPOT to reweight source prototypes and target samples, and design reweighted entropy loss and reweighted cross-entropy loss to distinguish "known" and "unknown" samples. Experiments on four benchmarks show that our method outperforms the previous state-of-the-art UniDA methods.

Related papers

• Inter-Domain Mixup for Semi-Supervised Domain Adaptation [108.40945109477886]
  Semi-supervised domain adaptation (SSDA) aims to bridge source and target domain distributions, with a small number of target labels available. Existing SSDA work fails to make full use of label information from both source and target domains for feature alignment across domains. This paper presents a novel SSDA approach, Inter-domain Mixup with Neighborhood Expansion (IDMNE), to tackle this issue.
  arXiv  Detail & Related papers  (2024-01-21T10:20:46Z)
• Semi-supervised Domain Adaptation via Prototype-based Multi-level Learning [4.232614032390374]
  In semi-supervised domain adaptation (SSDA), a few labeled target samples of each class help the model to transfer knowledge representation from the fully labeled source domain to the target domain. We propose a Prototype-based Multi-level Learning (ProML) framework to better tap the potential of labeled target samples.
  arXiv  Detail & Related papers  (2023-05-04T10:09:30Z)
• CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation [1.2691047660244335]
  Unsupervised Domain Adaptation (UDA) aims to align the labeled source distribution with the unlabeled target distribution to obtain domain invariant predictive models. We propose Contrastive Learning framework for semi-supervised Domain Adaptation (CLDA) that attempts to bridge the intra-domain gap. CLDA achieves state-of-the-art results on all the above datasets.
  arXiv  Detail & Related papers  (2021-06-30T20:23:19Z)
• Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation [22.852237073492894]
  Unsupervised Domain Adaptation (UDA) aims to generalize the knowledge learned from a well-labeled source domain to an unlabeled target domain. We propose a cross-domain discrepancy minimization (CGDM) method which explicitly minimizes the discrepancy of gradients generated by source samples and target samples. In order to compute the gradient signal of target samples, we further obtain target pseudo labels through a clustering-based self-supervised learning.
  arXiv  Detail & Related papers  (2021-06-08T07:35:40Z)
• Select, Label, and Mix: Learning Discriminative Invariant Feature Representations for Partial Domain Adaptation [55.73722120043086]
  We develop a "Select, Label, and Mix" (SLM) framework to learn discriminative invariant feature representations for partial domain adaptation. First, we present a simple yet efficient "select" module that automatically filters out outlier source samples to avoid negative transfer. Second, the "label" module iteratively trains the classifier using both the labeled source domain data and the generated pseudo-labels for the target domain to enhance the discriminability of the latent space.
  arXiv  Detail & Related papers  (2020-12-06T19:29:32Z)
• Domain Generalization via Semi-supervised Meta Learning [7.722498348924133]
  We propose the first method of domain generalization to leverage unlabeled samples. It is trained by a meta learning approach to mimic the distribution shift between the input source domains and unseen target domains. Experimental results on benchmark datasets indicate that DG outperforms state-of-the-art domain generalization and semi-supervised learning methods.
  arXiv  Detail & Related papers  (2020-09-26T18:05:04Z)
• Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation [67.83872616307008]
  Unversarial Domain adaptation (UDA) attempts to recognize the unlabeled target samples by building a learning model from a differently-distributed labeled source domain. In this paper, we propose a novel Adrial Dual Distincts Network (AD$2$CN) to align the source and target domain data distribution simultaneously with matching task-specific category boundaries. To be specific, a domain-invariant feature generator is exploited to embed the source and target data into a latent common space with the guidance of discriminative cross-domain alignment.
  arXiv  Detail & Related papers  (2020-08-27T01:29:10Z)
• Mining Label Distribution Drift in Unsupervised Domain Adaptation [78.2452946757045]
  We propose Label distribution Matching Domain Adversarial Network (LMDAN) to handle data distribution shift and label distribution drift jointly. Experiments show that LMDAN delivers superior performance under considerable label distribution drift.
  arXiv  Detail & Related papers  (2020-06-16T23:41:42Z)
• Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentation [97.8552697905657]
  A key challenge of this task is how to alleviate the data distribution discrepancy between the source and target domains. We propose Alleviating Semantic-level Shift (ASS), which can successfully promote the distribution consistency from both global and local views. We apply our ASS to two domain adaptation tasks, from GTA5 to Cityscapes and from Synthia to Cityscapes.
  arXiv  Detail & Related papers  (2020-04-02T03:25:05Z)

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.