Dual-model Collaboration Consistency Semi-Supervised Learning for Few-shot Lithology Interpretation

W Han, Z Fu, S Xiao, X Zheng, X Huang… - … on Geoscience and …, 2024 - ieeexplore.ieee.org
Remote sensing of the geological environment (GERS) interpretation contributes to
lithological mapping, disaster prediction, soil erosion monitoring, etc. However, the rich …

Updating road maps at city scale with remote sensed images and existing vector maps

X Chen, A Yu, Q Sun, W Guo, Q Xu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Currently, many countries have built geoinformation databases and gathered large amounts
of geographic data. However, with the extensive construction of infrastructure and rapid …

Enhancing the utilization of uncertain pixels in semi-supervised semantic segmentation

X Chang, C Chen, C Shan - Neurocomputing, 2024 - Elsevier
In semi-supervised semantic segmentation, determining the correct label for uncertain pixels
is crucial yet challenging. The recently proposed virtual category (VC) learning achieves …

CoNPL: Consistency training framework with noise-aware pseudo labeling for dense pose estimation

J Wen, T Chu, J Sun, Q Liu - Image and Vision Computing, 2024 - Elsevier
Dense pose estimation faces hurdles due to the lack of costly precise pixel-level IUV labels.
Existing methods aim to overcome it by regularizing model outputs or interpolating pseudo …

AMED: Automatic Mixed-Precision Quantization for Edge Devices

M Kimhi, T Rozen, A Mendelson, C Baskin - Mathematics, 2024 - mdpi.com
Quantized neural networks are well known for reducing the latency, power consumption,
and model size without significant harm to the performance. This makes them highly …

A Multi-View Integrated Ensemble for the Background Discrimination of Semi-Supervised Semantic Segmentation

H Gwak, Y Jeong, C Kim, Y Lee, S Yang, S Kim - Applied Sciences, 2023 - mdpi.com
The key to semi-supervised semantic segmentation is to assign the appropriate pseudo-
label to the pixels of unlabeled images. Recently, various approaches to consistency-based …

Boundary-refined prototype generation: A general end-to-end paradigm for semi-supervised semantic segmentation

J Dong, Z Meng, D Liu, J Liu, Z Zhao, F Su - Engineering Applications of …, 2024 - Elsevier
Semi-supervised semantic segmentation has attracted increasing attention in computer
vision, aiming to leverage unlabeled data through latent supervision. To achieve this goal …