Adapting Object Detectors with Conditional Domain Normalization

• URL: http://arxiv.org/abs/2003.07071v2
• Date: Wed, 22 Jul 2020 04:18:13 GMT
• Title: Adapting Object Detectors with Conditional Domain Normalization
• Authors: Peng Su, Kun Wang, Xingyu Zeng, Shixiang Tang, Dapeng Chen, Di Qiu, Xiaogang Wang
• Abstract summary: Conditional Domain Normalization (CDN) is designed to encode different domain inputs into a shared latent space. We incorporate CDN into various convolution stages of an object detector to adaptively address the domain shifts of different level's representation. Tests show that CDN outperforms existing methods remarkably on both real-to-real and synthetic-to-real adaptation benchmarks.
• Score: 38.13526570506076
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world object detectors are often challenged by the domain gaps between different datasets. In this work, we present the Conditional Domain Normalization (CDN) to bridge the domain gap. CDN is designed to encode different domain inputs into a shared latent space, where the features from different domains carry the same domain attribute. To achieve this, we first disentangle the domain-specific attribute out of the semantic features from one domain via a domain embedding module, which learns a domain-vector to characterize the corresponding domain attribute information. Then this domain-vector is used to encode the features from another domain through a conditional normalization, resulting in different domains' features carrying the same domain attribute. We incorporate CDN into various convolution stages of an object detector to adaptively address the domain shifts of different level's representation. In contrast to existing adaptation works that conduct domain confusion learning on semantic features to remove domain-specific factors, CDN aligns different domain distributions by modulating the semantic features of one domain conditioned on the learned domain-vector of another domain. Extensive experiments show that CDN outperforms existing methods remarkably on both real-to-real and synthetic-to-real adaptation benchmarks, including 2D image detection and 3D point cloud detection.

Related papers

• Unsupervised Domain Adaptation for Extra Features in the Target Domain Using Optimal Transport [3.6042575355093907]
  Most domain adaptation methods assume that the source and target domains have the same dimensionality. In this paper, it is assumed that common features exist in both domains and that extra (new additional) features are observed in the target domain. To leverage the homogeneity of the common features, the adaptation between these source and target domains is formulated as an optimal transport problem.
  arXiv  Detail & Related papers  (2022-09-10T04:35:58Z)
• Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptation [31.150256154504696]
  Unsupervised Domain Adaptation (UDA) has propelled the deployment of deep learning from limited experimental datasets into real-world unconstrained domains. Most UDA approaches align features within a common embedding space and apply a shared classifier for target prediction. We propose to simultaneously conduct feature alignment in two individual spaces focusing on different domains, and create for each space a domain-oriented classifier.
  arXiv  Detail & Related papers  (2022-08-02T01:38:37Z)
• Domain Invariant Masked Autoencoders for Self-supervised Learning from Multi-domains [73.54897096088149]
  We propose a Domain-invariant Masked AutoEncoder (DiMAE) for self-supervised learning from multi-domains. The core idea is to augment the input image with style noise from different domains and then reconstruct the image from the embedding of the augmented image. Experiments on PACS and DomainNet illustrate that DiMAE achieves considerable gains compared with recent state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-05-10T09:49:40Z)
• Dynamic Instance Domain Adaptation [109.53575039217094]
  Most studies on unsupervised domain adaptation assume that each domain's training samples come with domain labels. We develop a dynamic neural network with adaptive convolutional kernels to generate instance-adaptive residuals to adapt domain-agnostic deep features to each individual instance. Our model, dubbed DIDA-Net, achieves state-of-the-art performance on several commonly used single-source and multi-source UDA datasets.
  arXiv  Detail & Related papers  (2022-03-09T20:05:54Z)
• Exploiting Both Domain-specific and Invariant Knowledge via a Win-win Transformer for Unsupervised Domain Adaptation [14.623272346517794]
  Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Most existing UDA approaches enable knowledge transfer via learning domain-invariant representation and sharing one classifier across two domains. We propose a Win-Win TRansformer framework (WinTR) that separately explores the domain-specific knowledge for each domain and interchanges cross-domain knowledge.
  arXiv  Detail & Related papers  (2021-11-25T06:45:07Z)
• Vector-Decomposed Disentanglement for Domain-Invariant Object Detection [75.64299762397268]
  We try to disentangle domain-invariant representations from domain-specific representations. In the experiment, we evaluate our method on the single- and compound-target case.
  arXiv  Detail & Related papers  (2021-08-15T07:58:59Z)
• 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)
• 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)
• Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation [56.94873619509414]
  Conventional unsupervised domain adaptation studies the knowledge transfer between a limited number of domains. We propose a novel Domain2Vec model to provide vectorial representations of visual domains based on joint learning of feature disentanglement and Gram matrix. We demonstrate that our embedding is capable of predicting domain similarities that match our intuition about visual relations between different domains.
  arXiv  Detail & Related papers  (2020-07-17T22:05:09Z)

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.