Interventional Domain Adaptation

• URL: http://arxiv.org/abs/2011.03737v1
• Date: Sat, 7 Nov 2020 09:53:13 GMT
• Title: Interventional Domain Adaptation
• Authors: Jun Wen, Changjian Shui, Kun Kuang, Junsong Yuan, Zenan Huang, Zhefeng Gong, Nenggan Zheng
• Abstract summary: Domain adaptation (DA) aims to transfer discriminative features learned from source domain to target domain. Standard domain-invariance learning suffers from spurious correlations and incorrectly transfers the source-specifics. We create counterfactual features that distinguish the domain-specifics from domain-sharable part.
• Score: 81.0692660794765
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Domain adaptation (DA) aims to transfer discriminative features learned from source domain to target domain. Most of DA methods focus on enhancing feature transferability through domain-invariance learning. However, source-learned discriminability itself might be tailored to be biased and unsafely transferable by spurious correlations, \emph{i.e.}, part of source-specific features are correlated with category labels. We find that standard domain-invariance learning suffers from such correlations and incorrectly transfers the source-specifics. To address this issue, we intervene in the learning of feature discriminability using unlabeled target data to guide it to get rid of the domain-specific part and be safely transferable. Concretely, we generate counterfactual features that distinguish the domain-specifics from domain-sharable part through a novel feature intervention strategy. To prevent the residence of domain-specifics, the feature discriminability is trained to be invariant to the mutations in the domain-specifics of counterfactual features. Experimenting on typical \emph{one-to-one} unsupervised domain adaptation and challenging domain-agnostic adaptation tasks, the consistent performance improvements of our method over state-of-the-art approaches validate that the learned discriminative features are more safely transferable and generalize well to novel domains.

Related papers

• Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignment [35.67771212285966]
  This work studies the generalization issue of face anti-spoofing (FAS) models on domain gaps, such as image resolution, blurriness and sensor variations. We formulate this FAS strategy of separability and alignment (SA-FAS) as a problem of invariant risk minimization (IRM) We demonstrate the effectiveness of SA-FAS on challenging cross-domain FAS datasets and establish state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-03-23T20:34:27Z)
• 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)
• Self-Adversarial Disentangling for Specific Domain Adaptation [52.1935168534351]
  Domain adaptation aims to bridge the domain shifts between the source and target domains. Recent methods typically do not consider explicit prior knowledge on a specific dimension.
  arXiv  Detail & Related papers  (2021-08-08T02:36:45Z)
• Enhanced Separable Disentanglement for Unsupervised Domain Adaptation [6.942003070153651]
  Domain adaptation aims to mitigate the domain gap when transferring knowledge from an existing labeled domain to a new domain. Existing disentanglement-based methods do not fully consider separation between domain-invariant and domain-specific features. In this paper, we propose a novel enhanced separable disentanglement model.
  arXiv  Detail & Related papers  (2021-06-22T16:50:53Z)
• Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification [87.72851934197936]
  Unsupervised domain adaptive (UDA) person re-identification (ReID) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain for person matching. One challenge is how to generate target domain samples with reliable labels for training. We propose a Disentanglement-based Cross-Domain Feature Augmentation strategy.
  arXiv  Detail & Related papers  (2021-03-25T15:28:41Z)
• Re-energizing Domain Discriminator with Sample Relabeling for Adversarial Domain Adaptation [88.86865069583149]
  Unsupervised domain adaptation (UDA) methods exploit domain adversarial training to align the features to reduce domain gap. In this work, we propose an efficient optimization strategy named Re-enforceable Adversarial Domain Adaptation (RADA) RADA aims to re-energize the domain discriminator during the training by using dynamic domain labels.
  arXiv  Detail & Related papers  (2021-03-22T08:32:55Z)
• Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignment [11.74643883335152]
  Unsupervised domain adaptation is a promising avenue which transfers knowledge from a source domain to a target domain. We propose distance metric guided feature alignment (MetFA) to extract discriminative as well as domain-invariant features on both source and target domains. Our model integrates class distribution alignment to transfer semantic knowledge from a source domain to a target domain.
  arXiv  Detail & Related papers  (2020-08-19T13:36:57Z)
• Towards Stable and Comprehensive Domain Alignment: Max-Margin Domain-Adversarial Training [38.12978698952838]
  We propose a novel Max-margin Domain-Adversarial Training (MDAT) by designing an Adversarial Reconstruction Network (ARN) ARN conducts both feature-level and pixel-level domain alignment without involving extra network structures. Our approach outperforms other state-of-the-art domain alignment methods.
  arXiv  Detail & Related papers  (2020-03-30T07:48:52Z)
• Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels [78.95901454696158]
  We propose a novel Cross-Domain Self-supervised learning approach for domain adaptation. Our method significantly boosts performance of target accuracy in the new target domain with few source labels.
  arXiv  Detail & Related papers  (2020-03-18T15:11:07Z)

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.