L-dawa: Layer-wise divergence aware weight aggregation in federated self-supervised visual representation learning
YAU Rehman, Y Gao… - Proceedings of the …, 2023 - openaccess.thecvf.com
The ubiquity of camera-enabled devices has led to large amounts of unlabeled image data
being produced at the edge. The integration of self-supervised learning (SSL) and federated …
being produced at the edge. The integration of self-supervised learning (SSL) and federated …
[HTML][HTML] Real-time semantic segmentation with context aggregation network
With the increasing demand of autonomous systems, pixelwise semantic segmentation for
visual scene understanding needs to be not only accurate but also efficient for potential real …
visual scene understanding needs to be not only accurate but also efficient for potential real …
Cabinet: Efficient context aggregation network for low-latency semantic segmentation
With the increasing demand of autonomous machines, pixel-wise semantic segmentation for
visual scene understanding needs to be not only accurate but also efficient for any potential …
visual scene understanding needs to be not only accurate but also efficient for any potential …
[HTML][HTML] River water segmentation in surveillance camera images: A comparative study of offline and online augmentation using 32 CNNs
To obtain reliable water segmentations from image data for real-time monitoring of river
water levels, a comparison of 32 convolutional neural networks was performed. They were …
water levels, a comparison of 32 convolutional neural networks was performed. They were …
Learning dynamic network using a reuse gate function in semi-supervised video object segmentation
Current state-of-the-art approaches for Semi-supervised Video Object Segmentation (Semi-
VOS) propagates information from previous frames to generate segmentation mask for the …
VOS) propagates information from previous frames to generate segmentation mask for the …
Federated self-supervised learning for video understanding
The ubiquity of camera-enabled mobile devices has lead to large amounts of unlabelled
video data being produced at the edge. Although various self-supervised learning (SSL) …
video data being produced at the edge. Although various self-supervised learning (SSL) …
GRIB: Combining Global Reception and Inductive Bias For Human Segmentation and Matting
Human video segmentation and matting are challenging computer vision tasks with many
applications such as background replacement or background editing. Numerous methods …
applications such as background replacement or background editing. Numerous methods …
[HTML][HTML] Portrait segmentation using ensemble of heterogeneous deep-learning models
Image segmentation plays a central role in a broad range of applications, such as medical
image analysis, autonomous vehicles, video surveillance and augmented reality. Portrait …
image analysis, autonomous vehicles, video surveillance and augmented reality. Portrait …
Exploiting temporal information in real-time portrait video segmentation
Portrait video segmentation has been widely used in applications such as online
conferencing and content creation. However, it is challenging for mobile devices with limited …
conferencing and content creation. However, it is challenging for mobile devices with limited …
Real-time portrait image retouching extended from DualBLN
X Zhang, D Yan, G Bian, C Lu, S Wang, Q Yan… - Expert Systems with …, 2024 - Elsevier
Towards the target of image retouching tasks, the three-dimension LookUp Table (3D LUT)
is a discrete 3D lattice that represents the color mapping to correct the inconsistent color of …
is a discrete 3D lattice that represents the color mapping to correct the inconsistent color of …