Semantic image segmentation: Two decades of research
Semantic image segmentation (SiS) plays a fundamental role in a broad variety of computer
vision applications, providing key information for the global understanding of an image. This …
vision applications, providing key information for the global understanding of an image. This …
Unsupervised domain adaptation for semantic image segmentation: a comprehensive survey
Semantic segmentation plays a fundamental role in a broad variety of computer vision
applications, providing key information for the global understanding of an image. Yet, the …
applications, providing key information for the global understanding of an image. Yet, the …
Towards fewer annotations: Active learning via region impurity and prediction uncertainty for domain adaptive semantic segmentation
Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively
generates pseudo labels on unlabeled target data and retrains the network. However …
generates pseudo labels on unlabeled target data and retrains the network. However …
DVSOD: RGB-D video salient object detection
Salient object detection (SOD) aims to identify standout elements in a scene, with recent
advancements primarily focused on integrating depth data (RGB-D) or temporal data from …
advancements primarily focused on integrating depth data (RGB-D) or temporal data from …
Bi3d: Bi-domain active learning for cross-domain 3d object detection
Abstract Unsupervised Domain Adaptation (UDA) technique has been explored in 3D cross-
domain tasks recently. Though preliminary progress has been made, the performance gap …
domain tasks recently. Though preliminary progress has been made, the performance gap …
Joint semantic mining for weakly supervised RGB-D salient object detection
Training saliency detection models with weak supervisions, eg, image-level tags or captions,
is appealing as it removes the costly demand of per-pixel annotations. Despite the rapid …
is appealing as it removes the costly demand of per-pixel annotations. Despite the rapid …
Annotator: A generic active learning baseline for lidar semantic segmentation
Active learning, a label-efficient paradigm, empowers models to interactively query an oracle
for labeling new data. In the realm of LiDAR semantic segmentation, the challenges stem …
for labeling new data. In the realm of LiDAR semantic segmentation, the challenges stem …
Dirichlet-based uncertainty calibration for active domain adaptation
Active domain adaptation (DA) aims to maximally boost the model adaptation on a new
target domain by actively selecting limited target data to annotate, whereas traditional active …
target domain by actively selecting limited target data to annotate, whereas traditional active …
Deep active learning for computer vision tasks: methodologies, applications, and challenges
M Wu, C Li, Z Yao - Applied Sciences, 2022 - mdpi.com
Active learning is a label-efficient machine learning method that actively selects the most
valuable unlabeled samples to annotate. Active learning focuses on achieving the best …
valuable unlabeled samples to annotate. Active learning focuses on achieving the best …
A large-scale climate-aware satellite image dataset for domain adaptive land-cover semantic segmentation
A few well-annotated datasets for land-cover semantic segmentation have recently been
introduced to advance the field of earth observation technologies. However, these datasets …
introduced to advance the field of earth observation technologies. However, these datasets …