Exploring Categorical Regularization for Domain Adaptive Object Detection

@article{Xu2020ExploringCR,
  title={Exploring Categorical Regularization for Domain Adaptive Object Detection},
  author={Chang-Dong Xu and Xingran Zhao and Xin Jin and Xiu-Shen Wei},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={11721-11730}
}
  • Chang-Dong Xu, Xingran Zhao, +1 author Xiu-Shen Wei
  • Published 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
In this paper, we tackle the domain adaptive object detection problem, where the main challenge lies in significant domain gaps between source and target domains. Previous work seeks to plainly align image-level and instance-level shifts to eventually minimize the domain discrepancy. However, they still overlook to match crucial image regions and important instances across domains, which will strongly affect domain shift mitigation. In this work, we propose a simple but effective categorical… Expand
Informative and Consistent Correspondence Mining for Cross-Domain Weakly Supervised Object Detection
Cross-domain weakly supervised object detection aims to adapt object-level knowledge from a fully labeled source domain dataset (i.e., with object bounding boxes) to train object detectors for targetExpand
Domain-Adaptive Object Detection via Uncertainty-Aware Distribution Alignment
TLDR
This paper proposes a Multi-level Entropy Attention Alignment method that consists of two main components: a Local Uncertainty Attentional Alignment module to accelerate the model better perceiving structure-invariant objects of interest by utilizing information theory to measure the uncertainty of each local region via the entropy of the pixel-wise domain classifier. Expand
Multi-Source Domain Adaptation for Object Detection
TLDR
A unified Faster RCNN based framework, termed Divide-and-Merge Spindle Network (DMSN), is proposed, which can simultaneously enhance domain invariance and preserve discriminative power and develops a novel pseudo subnet learning algorithm to approximate optimal parameters of pseudo target subset by weighted combination of parameters in different source subnets. Expand
Foreground-focused domain adaption for object detection
TLDR
This work proposes a novel foreground-focused domain adaptation (FFDA) framework which mines the loss of the domain discriminators to concentrate on the backpropagation of foreground loss and reaches the new state-of-the-art accuracy on adapting Cityscape to Foggy Cityscape dataset. Expand
Domain-Specific Suppression for Adaptive Object Detection
TLDR
The domain- specific suppression is proposed, an exemplary and generalizable constraint to the original convolution gradients in backpropagation to detach the two parts of directions and suppress the domain-specific one. Expand
RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
TLDR
Rotation Prediction and Consistency Learning (PRCL) is proposed, a framework complementing existing XDD methods for domain alignment by leveraging the two auxiliary tasks that encourage the model to be robust to changes in the image space. Expand
RPN Prototype Alignment For Domain Adaptive Object Detector
Recent years have witnessed great progress of object detection. However, due to the domain shift problem, applying the knowledge of an object detector learned from one specific domain to another oneExpand
Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency
  • Zhipeng Luo, Zhongang Cai, +7 authors Ziwei Liu
  • Computer Science
  • ArXiv
  • 2021
TLDR
A novel and unified framework, Multi-Level Consistency Network (MLC-Net), which employs a teacherstudent paradigm to generate adaptive and reliable pseudotargets and outperforms existing state-of-the-art methods (including those using additional target domain information) on standard benchmarks. Expand
Hierarchical Context Embedding for Region-based Object Detection
TLDR
This work presents a simple but effective Hierarchical Context Embedding (HCE) framework, which can be applied as a plug-and-play component, to facilitate the classification ability of a series of region-based detectors by mining contextual cues. Expand
Densely Semantic Enhancement for Domain Adaptive Region-free Detectors
Copyright © 2021 IEEE. Personal use of this material is permitted. However, permission to use this material for any other purposes must be obtained from the IEEE by sending an email toExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 44 REFERENCES
Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain Adaptation
TLDR
This paper proposes a two-step progressive domain adaptation technique by fine-tuning the detector on two types of artificially and automatically generated samples, and achieves an improvement of approximately 5 to 20 percentage points in terms of mean average precision (mAP) compared to the best-performing baselines. Expand
Domain Adaptive Faster R-CNN for Object Detection in the Wild
TLDR
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
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. Expand
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. Expand
Strong-Weak Distribution Alignment for Adaptive Object Detection
TLDR
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
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%. Expand
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. 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
TLDR
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
Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection
TLDR
A weak self-training (WST) method and adversarial background score regularization (BSR) for domain adaptive one-stage object detection that diminishes the adverse effects of inaccurate pseudo-labels to stabilize the learning procedure and effectively improves the performance of the one- stage object detection in unsupervised domain adaptation setting. Expand
Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model
TLDR
An object detection system that relies on a multi-region deep convolutional neural network that also encodes semantic segmentation-aware features that aims at capturing a diverse set of discriminative appearance factors and exhibits localization sensitivity that is essential for accurate object localization. Expand
...
1
2
3
4
5
...