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

• URL: http://arxiv.org/abs/2108.07142v1
• Date: Mon, 16 Aug 2021 15:16:47 GMT
• Title: PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation
• Authors: Qiqi Gu, Qianyu Zhou, Minghao Xu, Zhengyang Feng, Guangliang Cheng, Xuequan Lu, Jianping Shi, Lizhuang Ma
• Abstract summary: We observe that the Field of View (FoV) gap induces noticeable instance appearance differences between the source and target domains. Motivated by the observations, we propose the textbfPosition-Invariant Transform (PIT) to better align images in different domains.
• Score: 53.428312630479816
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 appearance differences between the source and target domains. We further discover that the FoV gap between two domains impairs domain adaptation performance under both the FoV-increasing (source FoV < target FoV) and FoV-decreasing cases. Motivated by the observations, we propose the \textbf{Position-Invariant Transform} (PIT) to better align images in different domains. We also introduce a reverse PIT for mapping the transformed/aligned images back to the original image space and design a loss re-weighting strategy to accelerate the training process. Our method can be easily plugged into existing cross-domain detection/segmentation frameworks while bringing about negligible computational overhead. Extensive experiments demonstrate that our method can soundly boost the performance on both cross-domain object detection and segmentation for state-of-the-art techniques. Our code is available at https://github.com/sheepooo/PIT-Position-Invariant-Transform.

Related papers

• GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain Gap [9.284539958686368]
  We tackle the challenging problem of unsupervised video domain adaptation (UVDA) for action recognition. We introduce a novel UVDA scenario, denoted as Kinetics->BABEL, with a more considerable domain gap in terms of both temporal dynamics and background shifts. We empirically validate that the proposed method shows significant improvement over the existing methods on the Kinetics->BABEL dataset with a large domain gap.
  arXiv  Detail & Related papers  (2023-11-21T09:27:30Z)
• Reducing Domain Gap in Frequency and Spatial domain for Cross-modality Domain Adaptation on Medical Image Segmentation [5.371816551086118]
  Unsupervised domain adaptation (UDA) aims to learn a model trained on source domain and performs well on unlabeled target domain. We propose a simple yet effective UDA method based on frequency and spatial domain transfer uner multi-teacher distillation framework. Our proposed method achieves superior performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-11-28T11:35:39Z)
• Exploring Consistency in Cross-Domain Transformer for Domain Adaptive Semantic Segmentation [51.10389829070684]
  Domain gap can cause discrepancies in self-attention. Due to this gap, the transformer attends to spurious regions or pixels, which deteriorates accuracy on the target domain. We propose adaptation on attention maps with cross-domain attention layers.
  arXiv  Detail & Related papers  (2022-11-27T02:40:33Z)
• PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation [100.6343963798169]
  Unsupervised Domain Adaptation (UDA) aims to enhance the generalization of the learned model to other domains. We propose a unified pixel- and patch-wise self-supervised learning framework, called PiPa, for domain adaptive semantic segmentation.
  arXiv  Detail & Related papers  (2022-11-14T18:31:24Z)
• Domain Adaptation for Object Detection using SE Adaptors and Center Loss [0.0]
  We introduce an unsupervised domain adaptation method built on the foundation of faster-RCNN to prevent drops in performance due to domain shift. We also introduce a family of adaptation layers that leverage the squeeze excitation mechanism called SE Adaptors to improve domain attention. Finally, we incorporate a center loss in the instance and image level representations to improve the intra-class variance.
  arXiv  Detail & Related papers  (2022-05-25T17:18:31Z)
• An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection [29.70695339406896]
  We propose an end-to-end Supervised Domain Adaptation framework for cross-domain Change Detection. Our SDACD presents collaborative adaptations from both image and feature perspectives with supervised learning. Our framework pushes several representative baseline models up to new State-Of-The-Art records.
  arXiv  Detail & Related papers  (2022-04-01T01:35:30Z)
• 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)
• Affinity Space Adaptation for Semantic Segmentation Across Domains [57.31113934195595]
  In this paper, we address the problem of unsupervised domain adaptation (UDA) in semantic segmentation. Motivated by the fact that source and target domain have invariant semantic structures, we propose to exploit such invariance across domains. We develop two affinity space adaptation strategies: affinity space cleaning and adversarial affinity space alignment.
  arXiv  Detail & Related papers  (2020-09-26T10:28:11Z)
• CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency [119.45667331836583]
  Unsupervised domain adaptation algorithms aim to transfer the knowledge learned from one domain to another. We present a novel pixel-wise adversarial domain adaptation algorithm.
  arXiv  Detail & Related papers  (2020-01-09T19:00:35Z)

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.