Related references
Note: Only part of the references are listed.
Article
Engineering, Electrical & Electronic
Qianyu Zhou et al.
Summary: This paper proposes a novel Context-Aware Mixup (CAMix) framework for domain adaptive semantic segmentation, which utilizes context dependency as explicit prior knowledge to enhance adaptability towards the target domain. Experimental results demonstrate the effectiveness of the proposed method against state-of-the-art approaches on widely-used UDA benchmarks.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
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)
Article
Computer Science, Artificial Intelligence
Christoph Kamann et al.
Summary: Researchers conducted a comprehensive study on the robustness of semantic segmentation models, finding that many networks perform well against real-world image corruptions but poorly against digitally corrupted data or weather corruptions.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Computer Science, Artificial Intelligence
Rui Gong et al.
Summary: The DLOW model generates smooth transitions between source and target domains, as well as diverse new styles of images. Additionally, it can create images with gradually changing fog density to enhance segmentation performance.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Viraj Prabhu et al.
Summary: SENTRY is a UDA algorithm that selectively minimizes or maximizes predictive entropy based on the predictive consistency of target instances under a committee of random image transformations, leading to significant improvements over existing methods in various benchmarks when combined with pseudolabel-based approximate target class balancing.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Christos Sakaridis et al.
Summary: The ACDC dataset consists of 4006 images equally distributed among four common adverse conditions, namely fog, nighttime, rain, and snow, for training and testing semantic segmentation methods. Each image is accompanied by high-quality fine pixel-level semantic annotation, a corresponding image of the same scene under normal conditions, and a binary mask to distinguish clear and uncertain semantic content within the image. This dataset supports both standard semantic segmentation and uncertainty-aware semantic segmentation, posing challenges to state-of-the-art supervised and unsupervised approaches while guiding future progress in the field.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Qin Wang et al.
Summary: Domain adaptation for semantic segmentation can be improved by leveraging self-supervised depth estimation guidance from both source and target domains. This approach involves learning task feature correlation and utilizing depth prediction discrepancies between source and target to refine semantic segmentation. The proposed method demonstrates state-of-the-art performance on benchmark tasks SYNTHIA-to-Cityscapes and GTA-to-Cityscapes.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Srinadh Bhojanapalli et al.
Summary: This study compares ViT models and ResNet baselines, finding that when pre-trained with sufficient data, ViT models are at least as robust as ResNet counterparts under a broad range of perturbations. The study also reveals that Transformers are robust to the removal of almost any single layer, showcasing their importance in classification despite high correlations among activations from later layers.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Nikita Araslanov et al.
Summary: This domain adaptation approach for semantic segmentation uses standard data augmentation techniques to ensure consistency of semantic predictions across image transformations, achieving high accuracy. Trained in a lightweight self-supervised framework, it does not require additional training rounds and is remarkably effective in improving segmentation accuracy.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Jaehoon Choi et al.
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
(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
Zhizhong Li et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2018)
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
Francois Chollet
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)