SSF-DAN: Separated Semantic Feature Based Domain Adaptation Network for Semantic Segmentation

Liang, Dingkong; Tan, Jingang; Yang, Huamin; Feng, Jianfeng; Xue, Xiangyang; Zheng, Qibao; Ye, Xiaoqing; Zhang, Xiaolin

doi:10.1109/iccv.2019.00107

Cited by 169 publications

(126 citation statements)

References 24 publications

Supporting

Mentioning

126

Contrasting

Order By: Relevance

“…Table 1 and 2 summarize the semantic segmentation results of our model and compare with the other UDA methods [9,8,10,18,17]. To have a fair comparison, all the segmentation networks shown in the tables are developed with ResNet-101.…”

Section: Results and Comparisonsmentioning

confidence: 99%

See 1 more Smart Citation

Self-Guided Adversarial Learning For Domain Adaptive Semantic Segmentation

Pang¹,

Chang²,

Hsu

2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Unsupervised domain adaptation has been introduced to generalize semantic segmentation models from labeled synthetic images to unlabeled real-world images. Although much effort was devoted to minimize the cross-domain gap, the segmentation results on real-world data remain highly unstable. In this paper, we discuss two main issues which hinder previous methods from achieving satisfactory results and propose a novel self-guided adversarial learning to leverage the capability of domain adaptation. Firstly, to deal with the unpredictable data variation in the real-world domain, we develop a self-guided adversarial learning method by selecting reliable target pixels as guidance to lead the adaptation of the other pixels. Secondly, to address the class-imbalanced issue, we devise the selection strategy in each class independently and incorporate this idea with a class-level adversarial learning in a unified framework. Experimental results show that the proposed method significantly improves the previous methods on several benchmark datasets.

show abstract

Section: Results and Comparisonsmentioning

confidence: 99%

“…The adversarial domain alignment has been conducted in image level These two authors contributed equally. [ 5,6], feature level [7,8], or output level [9,10,11]. Other techniques, such as pseudo-label re-training [12,13], curriculum learning [14,15], and source-data selection [16], have also been exploited to reduce the cross-domain gap.…”

Section: Introductionmentioning

confidence: 99%

Self-Guided Adversarial Learning For Domain Adaptive Semantic Segmentation

Pang¹,

Chang²,

Hsu

2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…Specifically, despite its simplicity, CCM outperforms previous state-of-the-art adversarial-training (denote as "AT") based method "SSF-DAN" [13] by +4.5% and +2.9% on GTA5 → Cityscapes and SYNTHIA → Cityscapes, respectively. Compared with methods established on self-training, CCM achieves comparable or even better results.…”

Section: Comparison With the State-of-the-artsmentioning

confidence: 94%

“…Self-training has been exploited in various tasks such as semi-supervised learning [25,21], domain adaptation [38,58], and noisy label learning [40,35]. [41,44,34,47,24,13] adopted adversarial training at feature level to learn domain-invariant features to reduce the discrepancy across domains. [18,8,27] applied adversarial training at the image level to make features invariant to illumination, color and other style factors.…”

Section: Related Workmentioning

confidence: 99%

“…And the training tries to utilize the knowledge learned from the source and mitigate the domain shift. Previous methods usually achieved the adapted model through the adversarial training [41,44,34,24,13,18,2,27] or by self-training [58,59,28,50]. All those methods employed the entire source domain data throughout the training process, which neglects the fact that not all the source images could contribute to the improvement of adaptation performance, especially at certain training stages.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Content-Consistent Matching for Domain Adaptive Semantic Segmentation

Kang

Liu

et al. 2020

Lecture Notes in Computer Science

113

View full text Add to dashboard Cite

This paper considers the adaptation of semantic segmentation from the synthetic source domain to the real target domain. Different from most previous explorations that often aim at developing adversarialbased domain alignment solutions, we tackle this challenging task from a new perspective, i.e., content-consistent matching (CCM). The target of CCM is to acquire those synthetic images that share similar distribution with the real ones in the target domain, so that the domain gap can be naturally alleviated by employing the content-consistent synthetic images for training. To be specific, we facilitate the CCM from two aspects, i.e., semantic layout matching and pixel-wise similarity matching. First, we use all the synthetic images from the source domain to train an initial segmentation model, which is then employed to produce coarse pixel-level labels for the unlabeled images in the target domain. With the coarse/accurate label maps for real/synthetic images, we construct their semantic layout matrixes from both horizontal and vertical directions and perform the matrixes matching to find out the synthetic images with similar semantic layout to real images. Second, we choose those predicted labels with high confidence to generate feature embeddings for all classes in the target domain, and further perform the pixel-wise matching on the mined layout-consistent synthetic images to harvest the appearance-consistent pixels. With the proposed CCM, only those content-consistent synthetic images are taken into account for learning the segmentation model, which can effectively alleviate the domain bias caused by those content-irrelevant synthetic images. Extensive experiments are conducted on two popular domain adaptation tasks, i.e., GTA5− →Cityscapes and SYNTHIA− →Cityscapes. Our CCM yields consistent improvements over the baselines and performs favorably against previous state-of-the-arts.

show abstract

Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation

Subhani

Ali

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

SSF-DAN: Separated Semantic Feature Based Domain Adaptation Network for Semantic Segmentation

Cited by 169 publications

References 24 publications

Self-Guided Adversarial Learning For Domain Adaptive Semantic Segmentation

Self-Guided Adversarial Learning For Domain Adaptive Semantic Segmentation

Content-Consistent Matching for Domain Adaptive Semantic Segmentation

Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation

Contact Info

Product

Resources

About