Open Set Domain Adaptation using Optimal Transport

• URL: http://arxiv.org/abs/2010.01045v1
• Date: Fri, 2 Oct 2020 15:20:05 GMT
• Title: Open Set Domain Adaptation using Optimal Transport
• Authors: Marwa Kechaou, Romain H\'erault, Mokhtar Z. Alaya and Gilles Gasso
• Abstract summary: We present a 2-step optimal transport approach that performs a mapping from a source distribution to a target distribution. The first step aims at rejecting the samples issued from these new classes using an optimal transport plan. The second step solves the target (class ratio) shift still as an optimal transport problem.
• Score: 8.076841611508486
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a 2-step optimal transport approach that performs a mapping from a source distribution to a target distribution. Here, the target has the particularity to present new classes not present in the source domain. The first step of the approach aims at rejecting the samples issued from these new classes using an optimal transport plan. The second step solves the target (class ratio) shift still as an optimal transport problem. We develop a dual approach to solve the optimization problem involved at each step and we prove that our results outperform recent state-of-the-art performances. We further apply the approach to the setting where the source and target distributions present both a label-shift and an increasing covariate (features) shift to show its robustness.

Related papers

• Optimal Transport for Domain Adaptation through Gaussian Mixture Models [7.292229955481438]
  We propose a novel approach, where we model the data distributions through Gaussian mixture models. The optimal transport solution gives us a matching between source and target domain mixture components. We experiment with 2 domain adaptation benchmarks in fault diagnosis, showing that our methods have state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-03-18T09:32:33Z)
• A Class-aware Optimal Transport Approach with Higher-Order Moment Matching for Unsupervised Domain Adaptation [33.712557972990034]
  Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. We introduce a novel approach called class-aware optimal transport (OT), which measures the OT distance between a distribution over the source class-conditional distributions.
  arXiv  Detail & Related papers  (2024-01-29T08:27:31Z)
• MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation [98.09845149258972]
  We introduce active sample selection to assist domain adaptation regarding the semantic segmentation task. With only a little workload to manually annotate these samples, the distortion of the target-domain distribution can be effectively alleviated. A powerful semi-supervised domain adaptation strategy is proposed to alleviate the long-tail distribution problem.
  arXiv  Detail & Related papers  (2023-01-18T07:55:22Z)
• Fast OT for Latent Domain Adaptation [25.915629674463286]
  We propose an algorithm that uses optimal transport theory with a verifiably efficient and implementable solution to learn the best latent feature representation. This is achieved by minimizing the cost of transporting the samples from the target domain to the distribution of the source domain.
  arXiv  Detail & Related papers  (2022-10-02T10:25:12Z)
• Towards Optimization and Model Selection for Domain Generalization: A Mixup-guided Solution [43.292274574847234]
  We propose Mixup guided optimization and selection techniques for domain generalization. For optimization, we utilize an out-of-distribution dataset that can guide the preference direction. For model selection, we generate a validation dataset with a closer distance to the target distribution.
  arXiv  Detail & Related papers  (2022-09-01T02:18:00Z)
• Connecting adversarial attacks and optimal transport for domain adaptation [116.50515978657002]
  In domain adaptation, the goal is to adapt a classifier trained on the source domain samples to the target domain. In our method, we use optimal transport to map target samples to the domain named source fiction. Our main idea is to generate a source fiction by c-cyclically monotone transformation over the target domain.
  arXiv  Detail & Related papers  (2022-05-30T20:45:55Z)
• KL Guided Domain Adaptation [88.19298405363452]
  Domain adaptation is an important problem and often needed for real-world applications. A common approach in the domain adaptation literature is to learn a representation of the input that has the same distributions over the source and the target domain. We show that with a probabilistic representation network, the KL term can be estimated efficiently via minibatch samples.
  arXiv  Detail & Related papers  (2021-06-14T22:24:23Z)
• On Generating Transferable Targeted Perturbations [102.3506210331038]
  We propose a new generative approach for highly transferable targeted perturbations. Our approach matches the perturbed image distribution' with that of the target class, leading to high targeted transferability rates.
  arXiv  Detail & Related papers  (2021-03-26T17:55:28Z)
• Domain Adaptive Person Re-Identification via Coupling Optimization [58.567492812339566]
  Domain adaptive person Re-Identification (ReID) is challenging owing to the domain gap and shortage of annotations on target scenarios. This paper proposes a coupling optimization method including the Domain-Invariant Mapping (DIM) method and the Global-Local distance Optimization ( GLO) GLO is designed to train the ReID model with unsupervised setting on the target domain.
  arXiv  Detail & Related papers  (2020-11-06T14:01:03Z)
• Multi-source Domain Adaptation via Weighted Joint Distributions Optimal Transport [35.37752209765114]
  We propose a new approach to domain adaptation on unlabeled target datasets. We exploit the diversity of source distributions by tuning their weights to the target task at hand. Our method, named Weighted Joint Distribution Optimal Transport (WJDOT), aims at finding simultaneously an Optimal Transport-based alignment between the source and target distributions.
  arXiv  Detail & Related papers  (2020-06-23T12:33:30Z)
• Contradictory Structure Learning for Semi-supervised Domain Adaptation [67.89665267469053]
  Current adversarial adaptation methods attempt to align the cross-domain features. Two challenges remain unsolved: 1) the conditional distribution mismatch and 2) the bias of the decision boundary towards the source domain. We propose a novel framework for semi-supervised domain adaptation by unifying the learning of opposite structures.
  arXiv  Detail & Related papers  (2020-02-06T22:58:20Z)

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.