DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

Lai, Xin; Tian, Zhuotao; Xu, Xiaogang; Chen, Yingcong; Liu, Shu; Zhao, Hengshuang; Wang, Liwei; Jia, Jiaya

doi:10.1007/978-3-031-19827-4_22

Cited by 31 publications

(12 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since semantic segmentation training is highly dependent on a high-precision annotated dataset, the unsupervised domain adaptation (UDA) semantic segmentation task has attracted significant attention. The recent UDA work DecoupleNet [ 16 ] introduces an auxiliary classifier to learn more discriminative target domain features. The over-fitting of the source domain is alleviated so that the segmentation model can be more focused on the segmentation task.…”

Section: Related Workmentioning

confidence: 99%

Faster SCDNet: Real-Time Semantic Segmentation Network with Split Connection and Flexible Dilated Convolution

Tian

Yao

Chen

2023

Sensors

View full text Add to dashboard Cite

Recently, semantic segmentation has been widely applied in various realistic scenarios. Many semantic segmentation backbone networks use various forms of dense connection to improve the efficiency of gradient propagation in the network. They achieve excellent segmentation accuracy but lack inference speed. Therefore, we propose a backbone network SCDNet with a dual path structure and higher speed and accuracy. Firstly, we propose a split connection structure, which is a streamlined lightweight backbone with a parallel structure to increase inference speed. Secondly, we introduce a flexible dilated convolution using different dilation rates so that the network can have richer receptive fields to perceive objects. Then, we propose a three-level hierarchical module to effectively balance the feature maps with multiple resolutions. Finally, a refined flexible and lightweight decoder is utilized. Our work achieves a trade-off of accuracy and speed on the Cityscapes and Camvid datasets. Specifically, we obtain a 36% improvement in FPS and a 0.7% improvement in mIoU on the Cityscapes test set.

show abstract

Section: Related Workmentioning

confidence: 99%

Faster SCDNet: Real-Time Semantic Segmentation Network with Split Connection and Flexible Dilated Convolution

Tian

Yao

Chen

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…However, these models are difficult to optimize and often require fine-tuning of the model parameters. Zhang et al [48] established the two-stage training process of AT followed by ST. DecoupleNet [28] decouples ST and AT through two network branches to alleviate the difficulty of model training.…”

Section: Self-training For Udamentioning

confidence: 99%

“…Therefore, fine-tuning the network structure and the submodules parameters is generally needed, so that model performance depends on specific scenarios and loses its scalability and flexibility. Recently, several studies have been conducted to optimize and improve the process, such as decoupling AT and ST methods functionally by constructing dual-stream networks [28], and using exponential moving average (EMA) techniques to construct teacher networks to smooth instable features in the training process [29]. However, it also complicates the network architecture, increasing the spatial computational complexity, and reducing training efficiency.…”

Section: Introductionmentioning

confidence: 99%

“…The supervised information comes from generating higher quality pseudolabels One general conclusion about the DA performance of the model is: AT + ST > ST > AT [27]. However, as shown in Figure 1c, combining ST and AT methods typically requires strong coupling between submodules, which leads to a poorly stabilized model during training [28]. Therefore, fine-tuning the network structure and the submodules parameters is generally needed, so that model performance depends on specific scenarios and loses its scalability and flexibility.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning to Adapt Adversarial Perturbation Consistency for Domain Adaptive Semantic Segmentation of Remote Sensing Images

Xi,

Meng,

Chen

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Semantic segmentation techniques for remote sensing images (RSIs) have been widely developed and applied. However, most segmentation methods depend on sufficiently annotated data for specific scenarios. When a large change occurs in the target scenes, model performance drops significantly. Therefore, unsupervised domain adaptation (UDA) for semantic segmentation is proposed to alleviate the reliance on expensive per-pixel densely labeled data. In this paper, two key issues of existing domain adaptive (DA) methods are considered: (1) the factors that cause data distribution shifts in RSIs may be complex and diverse, and existing DA approaches cannot adaptively optimize for different domain discrepancy scenarios; (2) domain-invariant feature alignment, based on adversarial training (AT), is prone to excessive feature perturbation, leading to over robust models. To address these issues, we propose an AdvCDA method that guides the model to adapt adversarial perturbation consistency. We combine consistency regularization to consider interdomain feature alignment as perturbation information in the feature space, and thus propose a joint AT and self-training (ST) DA method to further promote the generalization performance of the model. Additionally, we propose a confidence estimation mechanism that determines network stream training weights so that the model can adaptively adjust the optimization direction. Extensive experiments have been conducted on Potsdam, Vaihingen, and LoveDA remote sensing datasets, and the results demonstrate that the proposed method can significantly improve the UDA performance in various cross-domain scenarios.

show abstract

“…The residual module can avoid the degradation problem caused by the too-deep network. Most recent semantic segmentation networks [4][5][6] stack many layers to improve accuracy. This design strategy cannot strike a good balance between accuracy and efficiency.…”

Section: Introductionmentioning

confidence: 99%

Edge-guided nonlinear dynamic convolution network for lightweight semantic segmentation

Zhang,

Xu,

et al. 2024

Second International Conference on Physics, Photonics, and Optical Engineering (ICPPOE 2023)

View full text Add to dashboard Cite

As the demand for autonomous driving and robot vision arises, semantic segmentation has developed rapidly. Semantic segmentation provides the means for machines to understand the environment. However, current methods face a balance issue between segmentation quality and computational resources. Our proposed Edge-Guided Non-linear Dynamic Convolutional Network (ENNet) achieves real-time and accurate semantic segmentation. The core of our network is a novel non-linear, dynamic combination (Nd-conv) that allows for a non-linear, dynamic combination (Nd-conv) of multiple convolution weights, improving the convolution's encoding ability while maintaining a low computational burden. The Non-linear Dynamic Convolutional Modules (NDCM), is introduced to enhance the segmentation accuracy of the network while maintaining efficiency. The multi-stage feature fusion module (MFFM) is also introduced to fuse low-level details and high-level semantic information to improve the segmentation accuracy of the network. Experiments conducted on a 1080Ti GPU show that our model achieves 74.6 mIOU on the Cityscapes dataset while being able to perform inference at 202 FPS. Our network design has achieved an optimal balance between speed and accuracy.

show abstract

DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

Cited by 31 publications

References 68 publications

Faster SCDNet: Real-Time Semantic Segmentation Network with Split Connection and Flexible Dilated Convolution

Faster SCDNet: Real-Time Semantic Segmentation Network with Split Connection and Flexible Dilated Convolution

Learning to Adapt Adversarial Perturbation Consistency for Domain Adaptive Semantic Segmentation of Remote Sensing Images

Edge-guided nonlinear dynamic convolution network for lightweight semantic segmentation

Contact Info

Product

Resources

About