Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification

• URL: http://arxiv.org/abs/2007.10315v1
• Date: Mon, 20 Jul 2020 17:57:02 GMT
• Title: Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification
• Authors: Yang Zou, Xiaodong Yang, Zhiding Yu, B.V.K. Vijaya Kumar, Jan Kautz
• Abstract summary: We propose a joint learning framework that disentangles id-related/unrelated features and enforces adaptation to work on the id-related feature space exclusively. Our model involves a disentangling module that encodes cross-domain images into a shared appearance space and two separate structure spaces, and an adaptation module that performs adversarial alignment and self-training on the shared appearance space.
• Score: 88.79480792084995
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although a significant progress has been witnessed in supervised person re-identification (re-id), it remains challenging to generalize re-id models to new domains due to the huge domain gaps. Recently, there has been a growing interest in using unsupervised domain adaptation to address this scalability issue. Existing methods typically conduct adaptation on the representation space that contains both id-related and id-unrelated factors, thus inevitably undermining the adaptation efficacy of id-related features. In this paper, we seek to improve adaptation by purifying the representation space to be adapted. To this end, we propose a joint learning framework that disentangles id-related/unrelated features and enforces adaptation to work on the id-related feature space exclusively. Our model involves a disentangling module that encodes cross-domain images into a shared appearance space and two separate structure spaces, and an adaptation module that performs adversarial alignment and self-training on the shared appearance space. The two modules are co-designed to be mutually beneficial. Extensive experiments demonstrate that the proposed joint learning framework outperforms the state-of-the-art methods by clear margins.

Related papers

• Joint Identifiability of Cross-Domain Recommendation via Hierarchical Subspace Disentanglement [19.29182848154183]
  Cross-Domain Recommendation (CDR) seeks to enable effective knowledge transfer across domains. While CDR describes user representations as a joint distribution over two domains, these methods fail to account for its joint identifiability. We propose a Hierarchical subspace disentanglement approach to explore the Joint IDentifiability of cross-domain joint distribution.
  arXiv  Detail & Related papers  (2024-04-06T03:11:31Z)
• Unsupervised Domain Adaptation via Style-Aware Self-intermediate Domain [52.783709712318405]
  Unsupervised domain adaptation (UDA) has attracted considerable attention, which transfers knowledge from a label-rich source domain to a related but unlabeled target domain. We propose a novel style-aware feature fusion method (SAFF) to bridge the large domain gap and transfer knowledge while alleviating the loss of class-discnative information.
  arXiv  Detail & Related papers  (2022-09-05T10:06:03Z)
• Unsupervised Contrastive Domain Adaptation for Semantic Segmentation [75.37470873764855]
  We introduce contrastive learning for feature alignment in cross-domain adaptation. The proposed approach consistently outperforms state-of-the-art methods for domain adaptation. It achieves 60.2% mIoU on the Cityscapes dataset.
  arXiv  Detail & Related papers  (2022-04-18T16:50:46Z)
• Self-semantic contour adaptation for cross modality brain tumor segmentation [13.260109561599904]
  We propose exploiting low-level edge information to facilitate the adaptation as a precursor task. The precise contour then provides spatial information to guide the semantic adaptation. We evaluate our framework on the BraTS2018 database for cross-modality segmentation of brain tumors.
  arXiv  Detail & Related papers  (2022-01-13T15:16:55Z)
• HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning [74.76431541169342]
  Zero-shot learning (ZSL) tackles the unseen class recognition problem, transferring semantic knowledge from seen classes to unseen ones. We propose a novel hierarchical semantic-visual adaptation (HSVA) framework to align semantic and visual domains. Experiments on four benchmark datasets demonstrate HSVA achieves superior performance on both conventional and generalized ZSL.
  arXiv  Detail & Related papers  (2021-09-30T14:27:50Z)
• AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection [90.18752912204778]
  Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. We propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training. Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations.
  arXiv  Detail & Related papers  (2021-06-10T05:01:20Z)
• Variational Interaction Information Maximization for Cross-domain Disentanglement [34.08140408283391]
  Cross-domain disentanglement is the problem of learning representations partitioned into domain-invariant and domain-specific representations. We cast the simultaneous learning of domain-invariant and domain-specific representations as a joint objective of multiple information constraints. We show that our model achieves the state-of-the-art performance in the zero-shot sketch based image retrieval task.
  arXiv  Detail & Related papers  (2020-12-08T07:11:35Z)
• Alleviating Human-level Shift : A Robust Domain Adaptation Method for Multi-person Pose Estimation [33.15192824888279]
  We propose a novel domain adaptation method for multi-person pose estimation. The main reason is that a pose, by nature, has typical topological structure and needs fine-grained features in local keypoints. Our method consists of three modules: Cross-Attentive Feature Alignment (CAFA), Intra-domain Structure Adaptation (ISA) and Inter-domain Human-Topology Alignment (IHTA)
  arXiv  Detail & Related papers  (2020-08-13T06:41:49Z)
• Context-Aware Domain Adaptation in Semantic Segmentation [59.79348089240319]
  We consider the problem of unsupervised domain adaptation in the semantic segmentation. Existing methods mainly focus on adapting domain-invariant features (what to transfer) through adversarial learning. We propose a cross-attention mechanism based on self-attention to capture context dependencies between two domains and adapt transferable context.
  arXiv  Detail & Related papers  (2020-03-09T09:57:24Z)

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.