no code implementations • 24 Apr 2024 • Tianyu Yan, Zifu Wan, Xinhao Deng, Pingping Zhang, Yang Liu, Huchuan Lu
In underwater scenes, it exhibits substantial performance degradation due to the light scattering and absorption.
1 code implementation • 7 Apr 2024 • Pingping Zhang, Tianyu Yan, Yang Liu, Huchuan Lu
To this end, we first introduce a dual structure with SAM's paradigm to enhance feature learning of marine images.
1 code implementation • 22 Oct 2023 • Tianyu Yan, Zifu Wan, Pingping Zhang, Gong Cheng, Huchuan Lu
To relieve these issues, in this work we propose a novel Transformer-based learning framework named TransY-Net for remote sensing image CD, which improves the feature extraction from a global view and combines multi-level visual features in a pyramid manner.
1 code implementation • 3 Oct 2022 • Tianyu Yan, Zifu Wan, Pingping Zhang
Then, we introduce a pyramid structure to aggregate multi-level visual features from Transformers for feature enhancement.
no code implementations • 3 Dec 2021 • Lianjie Jia, Chenyang Yu, Xiehao Ye, Tianyu Yan, Yinjie Lei, Pingping Zhang
To generate high-quality pseudo-labels and mitigate the impact of clustering errors, we propose a novel clustering relationship modeling framework for unsupervised person Re-ID.