Corpus ID: 237091087

PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation

  title={PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation},
  author={Qiqi Gu and Qianyu Zhou and Minghao Xu and Zhengyang Feng and Guangliang Cheng and Xuequan Lu and Jianping Shi and Lizhuang Ma},
Cross-domain object detection and semantic segmentation have witnessed impressive progress recently. Existing approaches mainly consider the domain shift resulting from external environments including the changes of background, illumination or weather, while distinct camera intrinsic parameters appear commonly in different domains and their influence for domain adaptation has been very rarely explored. In this paper, we observe that the Field of View (FoV) gap induces noticeable instance… Expand
Domain Adaptive Semantic Segmentation with Regional Contrastive Consistency Regularization
This work proposes a novel and fully end-to-end trainable approach, called regional contrastive consistency regularization (RCCR) for domain adaptive semantic segmentation, which outperforms the state-of-the-art methods on two common UDA benchmarks. Expand
Context-Aware Mixup for Domain Adaptive Semantic Segmentation
The proposed endto-end Context-Aware Mixup (CAMix) for domain adaptive semantic segmentation outperforms the state-of-the-art methods by a large margin on two widelyused domain adaptation benchmarks. Expand
Self-Adversarial Disentangling for Specific Domain Adaptation
A novel Self-Adversarial Disentangling (SAD) framework that achieves consistent improvements over state-of-the-art methods in both object detection and semantic segmentation tasks and mitigating the intra-domain gap. Expand
Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation
An uncertainty-aware consistency regularization method to tackle the issue for semantic segmentation by exploiting the latent uncertainty information of the target samples so that more meaningful and reliable knowledge from the teacher model would be transferred to the student model. Expand


Adapting Object Detectors via Selective Cross-Domain Alignment
The key idea is to mine the discriminative regions, namely those that are directly pertinent to object detection, and focus on aligning them across both domains, and perform remarkably better than existing methods. Expand
Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNN
This work proposes an asymmetric tri-way Faster-RCNN (ATF) for domain adaptive object detection, which has two distinct merits: 1) A ancillary net supervised by source label is deployed to learn anCillary target features and simultaneously preserve the discrimination of source domain, which enhances the structural discrimination of domain alignment. Expand
Domain Adaptive Faster R-CNN for Object Detection in the Wild
This work builds on the recent state-of-the-art Faster R-CNN model, and design two domain adaptation components, on image level and instance level, to reduce the domain discrepancy, based on $$-divergence theory. Expand
Strong-Weak Distribution Alignment for Adaptive Object Detection
This work proposes an approach for unsupervised adaptation of object detectors from label-rich to label-poor domains which can significantly reduce annotation costs associated with detection, and designs the strong domain alignment model to only look at local receptive fields of the feature map. Expand
Exploring Categorical Regularization for Domain Adaptive Object Detection
This work proposes a simple but effective categorical regularization framework for alleviating domain shift mitigation in the domain adaptive object detection problem, and obtains a significant performance gain over original Domain Adaptive Faster R-CNN detectors. Expand
SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses
A gradient detach based stacked complementary losses (SCL) method that uses detection losses as the primary objective, and cuts in several auxiliary losses in different network stages accompanying with gradient detach training to learn more discriminative representations. Expand
A Robust Learning Approach to Domain Adaptive Object Detection
A robust object detection framework that is resilient to noise in bounding box class labels, locations and size annotations is proposed that significantly improves the state-of-the-art on multiple domain adaptation scenarios on the SIM10K, Cityscapes and KITTI datasets. Expand
Exploring Object Relation in Mean Teacher for Cross-Domain Detection
This work presents Mean Teacher with Object Relations (MTOR) that novelly remolds Mean Teacher under the backbone of Faster R-CNN by integrating the object relations into the measure of consistency cost between teacher and student modules. Expand
Multi-Adversarial Faster-RCNN for Unrestricted Object Detection
  • Zhenwei He, Lei Zhang
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
A multi-adversarial Faster-RCNN (MAF) framework for unrestricted object detection, which inherently addresses domain disparity minimization for domain adaptation in feature representation and improves the domain adaptability. Expand
Cross-Domain Detection via Graph-Induced Prototype Alignment
A Graph-induced Prototype Alignment framework to seek for category-level domain alignment via elaborate prototype representations through graph-based information propagation among region proposals, and in order to alleviate the negative effect of class-imbalance on domain adaptation, a Class-reweighted Contrastive Loss is designed to harmonize the adaptation training process. Expand