Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Ao Ma et al.
Summary: This article proposes a novel domain adaptation scheme named adversarial entropy optimization (AEO), which improves model discriminability and promotes representation transferability by minimizing and maximizing entropy. This approach is well aligned with the core idea of adversarial learning and achieves state-of-the-art performance across diverse domain adaptation tasks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Engineering, Civil
Xiaohong Zhang et al.
Summary: In this paper, we propose a Mutual Encouragement Network (MENet) that simultaneously achieves semantic segmentation and depth estimation, and outperforms existing methods in experiments.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Engineering, Civil
Shiyu Liu et al.
Summary: This paper introduces the Built-in Depth-Semantic Coupled Encoding (BDSCE) module to improve scene parsing performance by effectively utilizing the correlation between depth and semantic information. The proposed module greatly enhances scene parsing results, especially in categories with clear depth distinction. Furthermore, the module is extended to other urban scene semantic reasoning tasks with successful outcomes.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Yuhui Yuan et al.
Summary: In this paper, a new context aggregation scheme called object context is proposed to enhance object information in semantic segmentation tasks. The method utilizes dense relation matrix and efficient interlaced sparse self-attention to model pixel relations, and combines with conventional multi-scale context schemes for richer context information. The approach shows competitive performances on challenging benchmarks like Cityscapes, ADE20K, LIP, PASCAL-Context, and COCO-Stuff.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yahao Liu et al.
Summary: This paper introduces a method based on boundary adaptation and prototype alignment, significantly boosting the performance of cross-domain semantic segmentation. By integrating boundary adaptation and prototype alignment, a discriminative and domain-invariant model is trained, leading to promising results in cross-domain semantic segmentation.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Automation & Control Systems
Xiaohong Zhang et al.
Summary: This study proposes a target-targeted domain adaptation approach focusing on training in the target domain, with an Image-to-image Translation (IIT) module for image space alignment and a Target-targeted Segmentation Adaptation (TSA) module for semantic segmentation at the target domain level. Experiments demonstrate the effectiveness of the method in domain adaptation of unsupervised semantic segmentation.
2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Xinyi Wu et al.
Summary: The proposed DANNet is a novel domain adaptation network for nighttime semantic segmentation, which does not require labeled nighttime image data. It utilizes adversarial training with a labeled daytime dataset and an unlabeled dataset containing coarsely aligned day-night image pairs, achieving domain adaptation between day and nighttime images.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Divya Kothandaraman et al.
Summary: This paper proposed a method called Domain Adaptive Knowledge Distillation to address the challenges of memory constraints and domain gap issues in practical autonomous driving systems. By introducing a new distillation strategy and cross entropy loss, the method successfully achieved unsupervised domain-adaptive semantic segmentation, showing significant success in experiments.
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WORKSHOPS (WACVW 2021)
(2021)
Article
Computer Science, Artificial Intelligence
Hanqing Xu et al.
Summary: This paper proposes a pixel-level consistency regularization method and a neutral cross-entropy loss based on consistency regularization, which mitigates the over-sharpness of entropy minimization through an internal neutralization mechanism. Experiments demonstrate that the proposed method outperforms state-of-the-art methods in the unsupervised domain adaptation problem of semantic segmentation.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Wei Zhou et al.
Summary: In this paper, the problem of unsupervised domain adaptation in semantic segmentation is addressed by leveraging co-occurring patterns between pairwise pixels in the output of structured semantic segmentation. Two affinity space adaptation strategies are developed for domain adaptation: affinity space cleaning and adversarial affinity space alignment. Extensive experiments show that the proposed method outperforms some state-of-the-art methods on challenging benchmarks for semantic segmentation across domains.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Yuxiao Zhang et al.
KNOWLEDGE-BASED SYSTEMS
(2020)
Article
Computer Science, Artificial Intelligence
Yang Zhang et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2020)
Article
Engineering, Civil
Lingli Zhou et al.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Tuan-Hung Vu et al.
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
(2019)
Article
Computer Science, Artificial Intelligence
Liang-Chieh Chen et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2018)
Article
Computer Science, Artificial Intelligence
Vijay Badrinarayanan et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Himalaya Jain et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Yi-Hsin Chen et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Fabio Maria Carlucci et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
