Confidence-and-Refinement Adaptation Model for Cross-Domain Semantic Segmentation

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 Confidenceand-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.

Class-conditional domain adaptation for semantic segmentation

“…We compared our method with six state-of-theart methods using image translation techniques: BDL [27], SEDA [50], LTIR [28], ITRA [48], CRA [31], and DPL [49]. Here, LTIR and CRA combine their proposed structures with existing image translation techniques (e.g., BDL), while others train their own image translation modules.…”

“…Additional techniques, such as image translation, can be combined with representation adaptation methods. Image translation focuses on narrowing down the domain shift between the source and target domains at the input image level by generating translated source domain images with target styles [27,31]. However, most existing domain adaptation methods for semantic segmentation tended to measure segmentation and adaptation globally, while ignoring the influence of different classes, which may affect their performance.…”

Advanced Learning Technologies for Intelligent Transportation Systems: Prospects and Challenges

“…In [189], the authors proposed a Confidence-Enhanced Mutual Graph Network (CE-MGN) to improve semantic segmentation and boundary detection under adverse weather conditions. Image features were converted into a graph representation using a mutual learning framework, incorporating a pairwise confidence-enhancement mechanism to model varying fog density effectively.…”