Divide and augment: Supervised domain adaptation via sample-wise feature fusion
Z Chen, B Pu, L Zhao, J He, P Liang - Information Fusion, 2025 - Elsevier
The training of deep models relies on appropriate regularization from a copious amount of
labeled data. And yet, obtaining a large and well-annotated dataset is costly. Thus …
labeled data. And yet, obtaining a large and well-annotated dataset is costly. Thus …
Mind Marginal Non-Crack Regions: Clustering-Inspired Representation Learning for Crack Segmentation
Crack segmentation datasets make great efforts to obtain the ground truth crack or non-crack
labels as clearly as possible. However it can be observed that ambiguities are still inevitable …
labels as clearly as possible. However it can be observed that ambiguities are still inevitable …
Non-stridden Convolution and Bidirectional Cross-Scale Features Fusion Network for Steel Surface Defect Detection
Z Xie, L Jin - International Conference on Intelligent Computing, 2024 - Springer
In the industrial production process of steel materials, various complex defects may appear
on the steel surface owing to the influence of environmental and other factors. These defects …
on the steel surface owing to the influence of environmental and other factors. These defects …
Large-scale Image Stitching Algorithm Integrating UAV Position Information and MGFT Model
Z Liu, J Liu, K Wang, J Tan, J Li - … International Conference on …, 2024 - ieeexplore.ieee.org
We propose a large-scale image stitching algorithm integrating UAV position information
and MGFT (Max Grad Feature with Transformer) model to deal with the issues of slow …
and MGFT (Max Grad Feature with Transformer) model to deal with the issues of slow …