DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

07/20/2022
by   Xin Lai, et al.
0

Unsupervised domain adaptation in semantic segmentation has been raised to alleviate the reliance on expensive pixel-wise annotations. It leverages a labeled source domain dataset as well as unlabeled target domain images to learn a segmentation network. In this paper, we observe two main issues of the existing domain-invariant learning framework. (1) Being distracted by the feature distribution alignment, the network cannot focus on the segmentation task. (2) Fitting source domain data well would compromise the target domain performance. To address these issues, we propose DecoupleNet that alleviates source domain overfitting and enables the final model to focus more on the segmentation task. Furthermore, we put forward Self-Discrimination (SD) and introduce an auxiliary classifier to learn more discriminative target domain features with pseudo labels. Finally, we propose Online Enhanced Self-Training (OEST) to contextually enhance the quality of pseudo labels in an online manner. Experiments show our method outperforms existing state-of-the-art methods, and extensive ablation studies verify the effectiveness of each component. Code is available at https://github.com/dvlab-research/DecoupleNet.

READ FULL TEXT
research
10/29/2019

Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation

Unsupervised domain adaptation (UDA) aims to enhance the generalization ...
research
10/04/2022

Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation

In this work we address multi-target domain adaptation (MTDA) in semanti...
research
07/16/2023

Dual-level Interaction for Domain Adaptive Semantic Segmentation

To circumvent the costly pixel-wise annotations of real-world images in ...
research
06/02/2023

Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning

Domain adaptive semantic segmentation enables robust pixel-wise understa...
research
10/13/2021

Domain Adaptive Semantic Segmentation without Source Data

Domain adaptive semantic segmentation is recognized as a promising techn...
research
10/21/2021

Exploiting Inter-pixel Correlations in Unsupervised Domain Adaptation for Semantic Segmentation

"Self-training" has become a dominant method for semantic segmentation v...
research
05/23/2023

Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation

Domain adaptive semantic segmentation aims to transfer knowledge from a ...

Please sign up or login with your details

Forgot password? Click here to reset