Domain Adaptive Faster R-CNN for Object Detection in the Wild

@article{Chen2018DomainAF,
  title={Domain Adaptive Faster R-CNN for Object Detection in the Wild},
  author={Yuhua Chen and Wen Li and Christos Sakaridis and Dengxin Dai and Luc Van Gool},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={3339-3348}
}
  • Yuhua Chen, Wen Li, +2 authors L. Gool
  • Published 8 March 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this work, we aim to improve the cross-domain robustness of object detection. We tackle the domain shift on two levels: 1) the image-level shift, such as image style, illumination, etc., and 2) the instance-level shift, such as object appearance, size, etc. We build… 
Domain-Invariant Region Proposal Network For Cross-Domain Detection
TLDR
A new design is proposed, Domain-Invariant RPN (DIR), which adopts adversarial learning to eliminate the domain shift in RPN, and thereby, significantly improving the accuracy and robustness of bounding box proposals.
Progressive Domain Adaptation for Object Detection
TLDR
This paper proposes to bridge the domain gap with an intermediate domain and progressively solve easier adaptation subtasks by adopting adversarial learning to align distributions at the feature level.
Region Proposal Oriented Approach for Domain Adaptive Object Detection
TLDR
This work addresses the domain adaptation problem in the context of object detection in the case where no annotations are available in the target domain by adapting the region proposal sub-network leading to a residual domain shift.
Adapting Object Detectors via Selective Cross-Domain Alignment
TLDR
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.
Multi-Level Domain Adaptive Learning for Cross-Domain Detection
TLDR
A multi-level domain adaptive model to simultaneously align the distributions of local- level features and global-level features is proposed and achieves superior performance against state-of-the-art techniques.
Multi-Scale Adversarial Cross-Domain Detection with Robust Discriminative Learning
TLDR
Experimental results show that the improving the performance of cross-domain detection from three perspectives outperforms the state-of-the-art for object detection under the setting of unsupervised domain adaptation (UDA).
Few-Shot Adaptive Faster R-CNN
TLDR
A novel few-shot adaptive Faster-RCNN framework, termed FAFRCNN, which effectively adapts to target domain with a few labeled samples, which achieves new state-of-the-art performance under both the interested few- shot domain adaptation (FDA) and unsupervised domain adaptation(UDA) setting.
Pixel and Feature Level Based Domain Adaption for Object Detection in Autonomous Driving
TLDR
A novel UDA model is presented to solve the more complex object detection problem in the context of autonomous driving and integrates both pixel level and feature level based transformtions to fulfill the cross domain detection task and can be further trained end-to-end to pursue better performance.
Deeply Aligned Adaptation for Cross-domain Object Detection
TLDR
This work proposes an end-to-end solution based on Faster R-CNN, where ground-truth annotations are available for source images but not for target ones during training, and develops a foreground-background aware alignment module to further reduce the domain mismatch.
Joint Feature-level and Pixel-level Domain Adaption for Object Detection in the Wild
  • Qianhui Luo, Yue Wang, Weijie Li, R. Xiong
  • Computer Science
    2019 IEEE 9th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER)
  • 2019
TLDR
A novel unsupervised domain adaption algorithm which improves the robustness of Faster R-CNN on two levels: on the feature level, a domain discriminator is appended to the feature extractor of faster R- CNN; on the pixel level, multiple feature maps from the feature Extractor are connected to a generator which feeds the fused features in a form of pictures to a laterdomain discriminator.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 67 REFERENCES
FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
TLDR
This paper introduces the first domain adaptive semantic segmentation method, proposing an unsupervised adversarial approach to pixel prediction problems, and outperforms baselines across different settings on multiple large-scale datasets.
R-FCN: Object Detection via Region-based Fully Convolutional Networks
TLDR
This work presents region-based, fully convolutional networks for accurate and efficient object detection, and proposes position-sensitive score maps to address a dilemma between translation-invariance in image classification and translation-variance in object detection.
Domain Adaptation of Deformable Part-Based Models
TLDR
This work introduces an adaptive structural SVM (A-SSVM) that adapts a pre-learned classifier between different domains that avoids accuracy drops as high as 15 points when comparing adapted and non-adapted detectors.
Subspace Alignment Based Domain Adaptation for RCNN Detector
TLDR
This paper shows that subspace alignment based domain adaptation of the state of the art RCNN based object detector can still adapt sub- spaces that are localized to the object by obtaining detections from the RCNN detector trained on source and applied on target.
Shifting Weights: Adapting Object Detectors from Image to Video
TLDR
This paper tackles the problem of adapting object detectors learned from images to work well on videos by seeking to iteratively adapt the detector by re-training the detector with automatically discovered target domain examples, starting with the easiest first.
Domain Generalization and Adaptation Using Low Rank Exemplar SVMs
TLDR
This paper proposes a new approach for domain generalization and domain adaptation based on exemplar SVMs based on logistic regression and least square SVM algorithms, which are referred to as LRE-SVMs and low rank exemplar least square SVMs (LRE-LSSVMs), respectively.
Deeper, Broader and Artier Domain Generalization
TLDR
This paper builds upon the favorable domain shift-robust properties of deep learning methods, and develops a low-rank parameterized CNN model for end-to-end DG learning that outperforms existing DG alternatives.
Geodesic flow kernel for unsupervised domain adaptation
TLDR
This paper proposes a new kernel-based method that takes advantage of low-dimensional structures that are intrinsic to many vision datasets, and introduces a metric that reliably measures the adaptability between a pair of source and target domains.
Open Set Domain Adaptation
TLDR
This work learns a mapping from the source to the target domain by jointly solving an assignment problem that labels those target instances that potentially belong to the categories of interest present in the source dataset.
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
...
1
2
3
4
5
...