Confidence-and-Refinement Adaptation Model for Cross-Domain Semantic Segmentation
- 13 January 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (7) , 9529-9542
Abstract
With the rapid development of convolutional neural networks (CNNs), significant progress has been achieved in semantic segmentation. Despite the great success, such deep learning approaches require large scale real-world datasets with pixel-level annotations. However, considering that pixel-level labeling of semantics is extremely laborious, many researchers turn to utilize synthetic data with free annotations. But due to the clear domain gap, the segmentation model trained with the synthetic images tends to perform poorly on the real-world datasets. Unsupervised domain adaptation (UDA) for semantic segmentation recently gains an increasing research attention, which aims at alleviating the domain discrepancy. Existing methods in this scope either simply align features or the outputs across the source and target domains or have to deal with the complex image processing and post-processing problems. In this work, we propose a novel multi-level UDA model named Confidence-and-Refinement Adaptation Model (CRAM), which contains a confidence-aware entropy alignment (CEA) module and a style feature alignment (SFA) module. Through CEA, the adaptation is done locally via adversarial learning in the output space, making the segmentation model pay attention to the high-confident predictions. Furthermore, to enhance the model transfer in the shallow feature space, the SFA module is applied to minimize the appearance gap across domains. Experiments on two challenging UDA benchmarks “GTA5-to-Cityscapes” and “SYNTHIA-to-Cityscapes” demonstrate the effectiveness of CRAM. We achieve comparable performance with the existing state-of-the-art works with advantages in simplicity and convergence speed.Keywords
Funding Information
- National Natural Science Foundation of China (61872187, 62072246, 62077023)
- Natural Science Foundation of Jiangsu Province (BK20201306)
- 111 Program (B13022)
This publication has 67 references indexed in Scilit:
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Image Style Transfer Using Convolutional Neural Networks2016
- Playing for Data: Ground Truth from Computer Games2016
- Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation2016
- The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes2016
- Deep Residual Learning for Image Recognition2016
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- Simultaneous Deep Transfer Across Domains and Tasks2015
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Fully convolutional networks for semantic segmentation2015