相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Automation & Control Systems
Zhen Fang et al.
Summary: The aim of unsupervised domain adaptation (UDA) is to utilize knowledge from a source domain to enhance the performance of a given target domain. To address the lack of accessible target domain labels, a new UDA setting called source domain reconstruction (SDR) is proposed, which constructs a new transferable source domain using labeled source samples and unlabeled target samples. Experimental results on seven benchmark datasets show that the reconstructed source domain has stronger transferability than the original source domain.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Mario Doebler et al.
Summary: Test-time adaptation (TTA) is a method proposed to deal with domain shifts during testing, and recently there emerged the area of continual and gradual TTA. In contrast to standard TTA which considers a single domain shift, continual TTA considers a sequence of shifts, and gradual TTA further exploits the property that some shifts evolve gradually over time. In this work, the authors propose that the symmetric cross-entropy is better suited as a consistency loss for mean teachers in TTA setting compared to the commonly used cross-entropy. The effectiveness of the proposed method robust mean teacher (RMT) is demonstrated on various benchmarks.
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR
(2023)
Article
Computer Science, Artificial Intelligence
Marcus de Carvalho et al.
Summary: This article discusses the problem of online unsupervised cross-domain adaptation and proposes the ACDC framework. It effectively addresses the challenges in data streams through a self-evolving neural network structure and achieves promising results in experiments.
KNOWLEDGE-BASED SYSTEMS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Oguzhan Fatih Kar et al.
Summary: We introduce a set of image transformations that take into account the geometry of the scene, making them more realistic compared to existing approaches. These transformations can be used to evaluate the robustness of models and serve as data augmentation mechanisms for training neural networks. The study shows that incorporating these transformations can expose vulnerabilities in existing models and improve the robustness of models when used as 3D data augmentation.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Inkyu Shin et al.
Summary: This paper proposes a new multi-modal test-time adaptation approach for 3D semantic segmentation. It includes two modules, intra-modal pseudo-label generation and inter-modal pseudo-label refinement, which provide stable self-learning signals in various multi-modal test-time adaptation scenarios.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Riccardo Volpi et al.
Summary: This paper proposes a new problem formulation and evaluation framework for advancing unsupervised domain adaptation in semantic image segmentation. The authors argue that traditional protocols for studying adaptation algorithms are not compatible with algorithms that can adapt to real-world situations, and thus propose a protocol where models need to learn online and continuously adapt from sequences of images.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Haibao Yu et al.
Summary: This article discusses the safety challenges faced by autonomous driving and the importance of vehicle-infrastructure cooperation. To accelerate computer vision research, the authors release the DAIR-V2X Dataset and introduce the problem of vehicle-infrastructure cooperative 3D object detection.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Qin Wang et al.
Summary: Test-time domain adaptation aims to adapt a source pretrained model to a continually changing target domain. We propose a continual test-time adaptation approach (CoTTA) to address distribution shift and catastrophic forgetting by reducing error accumulation and preserving source knowledge. CoTTA is easy to implement and outperforms existing methods in experiments.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yabin Zhang et al.
Summary: The study proposes an Exact Feature Distribution Matching (EFDM) method to address the problem of feature distribution matching by accurately matching the empirical Cumulative Distribution Functions (eCDFs) of image features. The method uses a fast Exact Histogram Matching (EHM) algorithm for implementation, improving computational efficiency and achieving state-of-the-art results in various visual learning tasks.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Jogendra Nath Kundu et al.
Summary: This study introduces a method for source-free domain adaptation in semantic segmentation by partitioning the task into source-only domain generalization and source-free target adaptation. The approach involves training a multi-head framework and utilizing reliable target pseudo-labels for self-training, as well as using a novel auto-encoder to enhance pseudo-label quality. Experimental results demonstrate the superiority of the proposed method compared to prior-arts and its compatibility with online adaptation for deployment in changing environments.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yuang Liu et al.
Summary: SFDA is a source-free domain adaptation framework for semantic segmentation, which recovers and preserves source domain knowledge through knowledge transfer, extracts valuable information from the target domain for self-supervised learning, and seamlessly integrates pixel- and patch-level optimization objectives tailored for semantic segmentation in the framework.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Xun Huang et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Article
Computer Science, Artificial Intelligence
Sinno Jialin Pan et al.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2010)
