Filters








3,448 Hits in 3.7 sec

Self-Ensembling GAN for Cross-Domain Semantic Segmentation [article]

Yonghao Xu, Fengxiang He, Bo Du, Liangpei Zhang, Dacheng Tao
2021 arXiv   pre-print
To mitigate the annotation burden, this paper proposes a self-ensembling generative adversarial network (SE-GAN) exploiting cross-domain data for semantic segmentation.  ...  In SE-GAN, a teacher network and a student network constitute a self-ensembling model for generating semantic segmentation maps, which together with a discriminator, forms a GAN.  ...  Luo et al. extended AdaptSeg with the category-level adversarial training to achieve finegrained domain adaptation [12].  ... 
arXiv:2112.07999v1 fatcat:7qzlasvwxzelpixbh7hvxrtqum

Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation [article]

Jaehoon Choi, Taekyung Kim, Changick Kim
2019 arXiv   pre-print
In this paper, we introduce a self-ensembling technique, one of the successful methods for domain adaptation in classification.  ...  To address this challenging issue, many researchers give attention to unsupervised domain adaptation for semantic segmentation.  ...  [48] utilize the self-ensembling attention network to extract attentionaware features for domain adaptation.  ... 
arXiv:1909.00589v1 fatcat:nkhcdpjps5dp7mzgcrfkbaojae

Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation [article]

Yawei Luo, Liang Zheng, Tao Guan, Junqing Yu, Yi Yang
2019 arXiv   pre-print
Specifically, we reduce the weight of the adversarial loss for category-level aligned features while increasing the adversarial force for those poorly aligned.  ...  Our idea is to take a close look at the category-level data distribution and align each class with an adaptive adversarial loss.  ...  By taking a close look at the category-level data distribution, CLAN adaptively weight the adversarial loss for each feature according to how well their category-level alignment is.  ... 
arXiv:1809.09478v3 fatcat:earkjibgn5a4poung6fjyrlgam

Consistency Regularization with High-dimensional Non-adversarial Source-guided Perturbation for Unsupervised Domain Adaptation in Segmentation [article]

Kaihong Wang, Chenhongyi Yang, Margrit Betke
2020 arXiv   pre-print
Unsupervised domain adaptation for semantic segmentation has been intensively studied due to the low cost of the pixel-level annotation for synthetic data.  ...  adaptation process.  ...  S2T stands for source domain to target domain image translation, T2S stands for target to source domain image translation, PL stands for pseudo-labeling and SE stands for self-ensembling.  ... 
arXiv:2009.08610v1 fatcat:ftslqpxe6bf45gpisrq6cbv5hu

MLSL: Multi-Level Self-Supervised Learning for Domain Adaptation with Spatially Independent and Semantically Consistent Labeling [article]

Javed Iqbal, Mohsen Ali
2019 arXiv   pre-print
In this paper, we propose a multi-level self-supervised learning model for domain adaptation of semantic segmentation.  ...  Our multi-level Self-supervised learning (MLSL) outperforms existing state-of art (self or adversarial learning) algorithms.  ...  In this work we propose category-based image classification using PWL and SISC based self-supervised learning for domain adaptation of semantic segmentation.  ... 
arXiv:1909.13776v1 fatcat:bbfmefaekra23eqge6elppmluy

A Review of Single-Source Deep Unsupervised Visual Domain Adaptation [article]

Sicheng Zhao, Xiangyu Yue, Shanghang Zhang, Bo Li, Han Zhao, Bichen Wu, Ravi Krishna, Joseph E. Gonzalez, Alberto L. Sangiovanni-Vincentelli, Sanjit A. Seshia, Kurt Keutzer
2020 arXiv   pre-print
We then summarize and compare different categories of single-source unsupervised domain adaptation methods, including discrepancy-based methods, adversarial discriminative methods, adversarial generative  ...  In this paper, we review the latest single-source deep unsupervised domain adaptation methods focused on visual tasks and discuss new perspectives for future research.  ...  Because of this, self-supervision tasks that predict high-level structural labels are more favorable for domain adaptation. Kim et al.  ... 
arXiv:2009.00155v3 fatcat:yqkew4n4q5gtbjosozufw37ome

Unsupervised Adaptive Semantic Segmentation with Local Lipschitz Constraint [article]

Guanyu Cai, Lianghua He
2021 arXiv   pre-print
non-adversarial adaptive semantic segmentation.  ...  Existing methods either align different domains with adversarial training or involve the self-learning that utilizes pseudo labels to conduct supervised training.  ...  Most adaptive semantic segmentation methods introduce adversarial training [12] , [24] , [25] to align the source and target domain in different levels.  ... 
arXiv:2105.12939v1 fatcat:m7ff6rhcqbdlblxdv3xfip3osu

Domain Adaptation based COVID-19 CT Lung Infections Segmentation Network [article]

Han Chen and Yifan Jiang and Hanseok Ko
2020 arXiv   pre-print
To overcome the domain mismatch, we introduce conditional GAN for adversarial training. We update the segmentation network with the cross-domain adversarial loss.  ...  In order to solve this issue, we propose a novel domain adaptation based COVID-19 CT lung infections segmentation network.  ...  This proves that the high-level semantic information is more helpful for domain adaptation than the rich details in the low-level features maps. We adopt this setting for our network.  ... 
arXiv:2011.11242v1 fatcat:nyu7cz2ccjd3znlz2ftbejapwi

A Survey of Unsupervised Deep Domain Adaptation [article]

Garrett Wilson, Diane J. Cook
2020 arXiv   pre-print
As a complement to this challenge, single-source unsupervised domain adaptation can handle situations where a network is trained on labeled data from a source domain and unlabeled data from a related but  ...  Many single-source and typically homogeneous unsupervised deep domain adaptation approaches have thus been developed, combining the powerful, hierarchical representations from deep learning with domain  ...  for pseudo-labeling target data. 3.4.1 Self-Ensembling.  ... 
arXiv:1812.02849v3 fatcat:paefg5cywbe3tjsp6dffnwkvxy

Known-class Aware Self-ensemble for Open Set Domain Adaptation [article]

Qing Lian, Wen Li, Lin Chen, Lixin Duan
2019 arXiv   pre-print
To tackle this challenge, we propose a new approach coined as Known-class Aware Self-Ensemble (KASE), which is built upon the recently developed self-ensemble model.  ...  Existing domain adaptation methods generally assume different domains have the identical label space, which is quite restrict for real-world applications.  ...  Self-ensemble for Domain Adaptation We build our model on the state-of-the-art self-ensemble model [French et al., 2018] .  ... 
arXiv:1905.01068v1 fatcat:fy3iwes5zfcdfeva4mzbupvxtu

Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey [article]

Gabriela Csurka, Riccardo Volpi, Boris Chidlovskii
2021 arXiv   pre-print
We present the most important semantic segmentation methods; we provide a comprehensive survey on domain adaptation techniques for semantic segmentation; we unveil newer trends such as multi-domain learning  ...  , domain generalization, test-time adaptation or source-free domain adaptation; we conclude this survey by describing datasets and benchmarks most widely used in semantic segmentation research.  ...  Self- [60] Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing ensembling for Visual Domain Adaptation.  ... 
arXiv:2112.03241v1 fatcat:uzlehddvuvfwzf4dfbjimja45e

Unsupervised Domain Adaptation in Semantic Segmentation: a Review [article]

Marco Toldo, Andrea Maracani, Umberto Michieli, Pietro Zanuttigh
2020 arXiv   pre-print
The aim of this paper is to give an overview of the recent advancements in the Unsupervised Domain Adaptation (UDA) of deep networks for semantic segmentation.  ...  Then, we introduce the different levels at which adaptation strategies may be applied: namely, at the input (image) level, at the internal features representation and at the output level.  ...  Recently, the student-teacher self-ensembling adaptation approach is extended by Zhou et al.  ... 
arXiv:2005.10876v1 fatcat:7t5v6qibxnfcxhwtohqqunhd2u

Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification [article]

Zhipeng Luo, Xiaobing Zhang, Shijian Lu, Shuai Yi
2021 arXiv   pre-print
for optimal pseudo label prediction and self-training.  ...  In this paper, we propose an end-to-end trainable network that exploits domain Consistency Regularization for unsupervised Multi-source domain Adaptive classification (CRMA).  ...  regularized self-training for multi-source unsupervised domain adaptation.  ... 
arXiv:2106.08590v1 fatcat:5rujqvspjjcj3ku4hfr7nbzpje

Unsupervised Domain Adaptation in Semantic Segmentation: A Review

Marco Toldo, Andrea Maracani, Umberto Michieli, Pietro Zanuttigh
2020 Technologies  
The aim of this paper is to give an overview of the recent advancements in the Unsupervised Domain Adaptation (UDA) of deep networks for semantic segmentation.  ...  Then, we introduce the different levels at which adaptation strategies may be applied: namely, at the input (image) level, at the internal features representation and at the output level.  ...  Recently, the student-teacher self-ensembling adaptation approach is extended by Zhou et al.  ... 
doi:10.3390/technologies8020035 fatcat:qzgjjiw5p5bldk76mh3s3pwlfq

Decoupled Adaptation for Cross-Domain Object Detection [article]

Junguang Jiang, Baixu Chen, Jianmin Wang, Mingsheng Long
2021 arXiv   pre-print
Besides, previous methods focused on category adaptation but ignored another important part for object detection, i.e., the adaptation on bounding box regression.  ...  To this end, we propose D-adapt, namely Decoupled Adaptation, to decouple the adversarial adaptation and the training of the detector.  ...  Local feature adaptation in the pixel level (Figure 1(c) ) can alleviate domain shift when the shift is primarily low-level, yet it will struggle when the domains are different at the semantic level.  ... 
arXiv:2110.02578v1 fatcat:yvqdwkzlh5cpnhfjvyvdyzo7em
« Previous Showing results 1 — 15 out of 3,448 results