Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation

• URL: http://arxiv.org/abs/2108.06962v1
• Date: Mon, 16 Aug 2021 08:36:10 GMT
• Title: Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation
• Authors: Antoine Saporta and Tuan-Hung Vu and Matthieu Cord and Patrick P\'erez
• Abstract summary: We address the task of unsupervised domain adaptation (UDA) for semantic segmentation in presence of multiple target domains. We introduce two adversarial frameworks: (i) multi-discriminator, which explicitly aligns each target domain to its counterparts, and (ii) multi-target knowledge transfer, which learns a target-agnostic model. In all tested scenarios, our approaches consistently outperform baselines, setting competitive standards for the novel task.
• Score: 32.39557675340562
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we address the task of unsupervised domain adaptation (UDA) for semantic segmentation in presence of multiple target domains: The objective is to train a single model that can handle all these domains at test time. Such a multi-target adaptation is crucial for a variety of scenarios that real-world autonomous systems must handle. It is a challenging setup since one faces not only the domain gap between the labeled source set and the unlabeled target set, but also the distribution shifts existing within the latter among the different target domains. To this end, we introduce two adversarial frameworks: (i) multi-discriminator, which explicitly aligns each target domain to its counterparts, and (ii) multi-target knowledge transfer, which learns a target-agnostic model thanks to a multi-teacher/single-student distillation mechanism.The evaluation is done on four newly-proposed multi-target benchmarks for UDA in semantic segmentation. In all tested scenarios, our approaches consistently outperform baselines, setting competitive standards for the novel task.

Related papers

• OurDB: Ouroboric Domain Bridging for Multi-Target Domain Adaptive Semantic Segmentation [8.450397069717727]
  Multi-target domain adaptation (MTDA) for semantic segmentation poses a significant challenge, as it involves multiple target domains with varying distributions. Previous MTDA approaches typically employ multiple teacher architectures, where each teacher specializes in one target domain to simplify the task. We propose an ouroboric domain bridging (OurDB) framework, offering an efficient solution to the MTDA problem using a single teacher architecture.
  arXiv  Detail & Related papers  (2024-03-18T08:55:48Z)
• Strong-Weak Integrated Semi-supervision for Unsupervised Single and Multi Target Domain Adaptation [6.472434306724611]
  Unsupervised domain adaptation (UDA) focuses on transferring knowledge learned in the labeled source domain to the unlabeled target domain. In this paper, we propose a novel strong-weak integrated semi-supervision (SWISS) learning strategy for image classification.
  arXiv  Detail & Related papers  (2023-09-12T19:08:54Z)
• ML-BPM: Multi-teacher Learning with Bidirectional Photometric Mixing for Open Compound Domain Adaptation in Semantic Segmentation [78.19743899703052]
  Open compound domain adaptation (OCDA) considers the target domain as the compound of multiple unknown homogeneous. We introduce a multi-teacher framework with bidirectional photometric mixing to adapt to every target subdomain. We conduct an adaptive distillation to learn a student model and apply consistency regularization to improve the student generalization.
  arXiv  Detail & Related papers  (2022-07-19T03:30:48Z)
• Discovering Domain Disentanglement for Generalized Multi-source Domain Adaptation [48.02978226737235]
  A typical multi-source domain adaptation (MSDA) approach aims to transfer knowledge learned from a set of labeled source domains, to an unlabeled target domain. We propose a variational domain disentanglement (VDD) framework, which decomposes the domain representations and semantic features for each instance by encouraging dimension-wise independence.
  arXiv  Detail & Related papers  (2022-07-11T04:33:08Z)
• Multi-Target Domain Adaptation with Collaborative Consistency Learning [105.7615147382486]
  We propose a collaborative learning framework to achieve unsupervised multi-target domain adaptation. The proposed method can effectively exploit rich structured information contained in both labeled source domain and multiple unlabeled target domains.
  arXiv  Detail & Related papers  (2021-06-07T08:36:20Z)
• Your Classifier can Secretly Suffice Multi-Source Domain Adaptation [72.47706604261992]
  Multi-Source Domain Adaptation (MSDA) deals with the transfer of task knowledge from multiple labeled source domains to an unlabeled target domain. We present a different perspective to MSDA wherein deep models are observed to implicitly align the domains under label supervision.
  arXiv  Detail & Related papers  (2021-03-20T12:44:13Z)
• Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation [102.42638795864178]
  We propose a principled meta-learning based approach to OCDA for semantic segmentation. We cluster target domain into multiple sub-target domains by image styles, extracted in an unsupervised manner. A meta-learner is thereafter deployed to learn to fuse sub-target domain-specific predictions, conditioned upon the style code. We learn to online update the model by model-agnostic meta-learning (MAML) algorithm, thus to further improve generalization.
  arXiv  Detail & Related papers  (2020-12-15T13:21:54Z)
• Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation [74.3349233035632]
  Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) do not consider an inter-class variation within the target domain itself or estimated category. We introduce a learnable clustering module, and a novel domain adaptation framework called cross-domain grouping and alignment. Our method consistently boosts the adaptation performance in semantic segmentation, outperforming the state-of-the-arts on various domain adaptation settings.
  arXiv  Detail & Related papers  (2020-12-15T11:36:21Z)
• MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation [58.38749495295393]
  Domain adaptation aims to learn a transferable model to bridge the domain shift between one labeled source domain and another sparsely labeled or unlabeled target domain. Recent multi-source domain adaptation (MDA) methods do not consider the pixel-level alignment between sources and target. We propose a novel MDA framework to address these challenges.
  arXiv  Detail & Related papers  (2020-02-19T21:22:00Z)

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.