RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks

• URL: http://arxiv.org/abs/2104.08689v1
• Date: Sun, 18 Apr 2021 02:56:19 GMT
• Title: RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
• Authors: Kai Li, Curtis Wigington, Chris Tensmeyer, Vlad I. Morariu, Handong Zhao, Varun Manjunatha, Nikolaos Barmpalios, Yun Fu
• Abstract summary: Cross-Domain Detection (XDD) aims to train an object detector using labeled image from a source domain but have good performance in the target domain with only unlabeled images. This paper provides a complementary solution to align domains by learning the same auxiliary tasks in both domains simultaneously.
• Score: 74.10747285807315
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cross-Domain Detection (XDD) aims to train an object detector using labeled image from a source domain but have good performance in the target domain with only unlabeled images. Existing approaches achieve this either by aligning the feature maps or the region proposals from the two domains, or by transferring the style of source images to that of target image. Contrasted with prior work, this paper provides a complementary solution to align domains by learning the same auxiliary tasks in both domains simultaneously. These auxiliary tasks push image from both domains towards shared spaces, which bridges the domain gap. Specifically, this paper proposes Rotation Prediction and Consistency Learning (PRCL), a framework complementing existing XDD methods for domain alignment by leveraging the two auxiliary tasks. The first one encourages the model to extract region proposals from foreground regions by rotating an image and predicting the rotation angle from the extracted region proposals. The second task encourages the model to be robust to changes in the image space by optimizing the model to make consistent class predictions for region proposals regardless of image perturbations. Experiments show the detection performance can be consistently and significantly enhanced by applying the two proposed tasks to existing XDD methods.

Related papers

• I2F: A Unified Image-to-Feature Approach for Domain Adaptive Semantic Segmentation [55.633859439375044]
  Unsupervised domain adaptation (UDA) for semantic segmentation is a promising task freeing people from heavy annotation work. Key idea to tackle this problem is to perform both image-level and feature-level adaptation jointly. This paper proposes a novel UDA pipeline for semantic segmentation that unifies image-level and feature-level adaptation.
  arXiv  Detail & Related papers  (2023-01-03T15:19:48Z)
• 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)
• Unsupervised Domain Adaptation with Variational Approximation for Cardiac Segmentation [15.2292571922932]
  Unsupervised domain adaptation is useful in medical image segmentation. We propose a new framework, where the latent features of both domains are driven towards a common and parameterized variational form. This is achieved by two networks based on variational auto-encoders (VAEs) and a regularization for this variational approximation.
  arXiv  Detail & Related papers  (2021-06-16T13:00:39Z)
• 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)
• Learning Unsupervised Cross-domain Image-to-Image Translation Using a Shared Discriminator [2.1377923666134118]
  Unsupervised image-to-image translation is used to transform images from a source domain to generate images in a target domain without using source-target image pairs. We propose a new method that uses a single shared discriminator between the two GANs, which improves the overall efficacy. Our results indicate that even without adding attention mechanisms, our method performs at par with attention-based methods and generates images of comparable quality.
  arXiv  Detail & Related papers  (2021-02-09T08:26:23Z)
• Deep Symmetric Adaptation Network for Cross-modality Medical Image Segmentation [40.95845629932874]
  Unsupervised domain adaptation (UDA) methods have shown their promising performance in the cross-modality medical image segmentation tasks. We present a novel deep symmetric architecture of UDA for medical image segmentation, which consists of a segmentation sub-network and two symmetric source and target domain translation sub-networks. Our method has remarkable advantages compared to the state-of-the-art methods in both cross-modality Cardiac and BraTS segmentation tasks.
  arXiv  Detail & Related papers  (2021-01-18T02:54:30Z)
• Bi-Dimensional Feature Alignment for Cross-Domain Object Detection [71.85594342357815]
  We propose a novel unsupervised cross-domain detection model. It exploits the annotated data in a source domain to train an object detector for a different target domain. The proposed model mitigates the cross-domain representation divergence for object detection.
  arXiv  Detail & Related papers  (2020-11-14T03:03:11Z)
• Adversarial Bipartite Graph Learning for Video Domain Adaptation [50.68420708387015]
  Domain adaptation techniques, which focus on adapting models between distributionally different domains, are rarely explored in the video recognition area. Recent works on visual domain adaptation which leverage adversarial learning to unify the source and target video representations are not highly effective on the videos. This paper proposes an Adversarial Bipartite Graph (ABG) learning framework which directly models the source-target interactions.
  arXiv  Detail & Related papers  (2020-07-31T03:48:41Z)
• Domain Conditioned Adaptation Network [90.63261870610211]
  We propose a Domain Conditioned Adaptation Network (DCAN) to excite distinct convolutional channels with a domain conditioned channel attention mechanism. This is the first work to explore the domain-wise convolutional channel activation for deep DA networks.
  arXiv  Detail & Related papers  (2020-05-14T04:23:24Z)

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.