Towards Complex Backgrounds: A Unified Difference-Aware Decoder for Binary Segmentation

Jiepan Li, Wei He, Hongyan Zhang

Code

• Introduction: A new unified dual-branch decoder paradigm named the difference-aware decoder is proposed in this paper to explore the difference between the foreground and the background and separate the objects of interest in optical images.
• Key words: Binary segmentation, camouflaged object detection, salient object detection, polyp segmentation, mirror detection.

UANet: an Uncertainty-Aware Network for Building Extraction from Remote Sensing Images

Jiepan Li, Wei He, Weinan Cao, Liangpei Zhang, Hongyan Zhang

IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2024. (SCI Q1 TOP, IF=8.2)

Code

• Introduction: In this paper, we realize the importance of uncertain prediction and propose a novel and straightforward Uncertainty-Aware Network (UANet) to alleviate this problem.
• Key words: Remote sensing, building extraction, uncertainty-aware

Cross-level Attention with Overlapped Windows for Camouflaged Object Detection

Jiepan Li, Fangxiao Lu, Nan Xue, Zhuohong Li, Hongyan Zhang, Wei He

Code

• Introduction: In this paper, we propose an overlapped window cross-level attention (OWinCA) to achieve the low-level feature enhancement guided by the highest-level features.
• Key words: Camouflaged Object Detection, Attention Mechanism

We ranked first in the track 1 of the Data Fusion Contest 2024（champion）

• Introduction: This track focuses on mapping the water surface from Copernicus Sentinel-1 SAR imagery. The goal is to accurately determine water and non-water pixels in these event areas by fusing data from one or more of the provided data sources.

• Key words: SAR, Flood rapid mapping

We ranked first in the track 2 of the Data Fusion Contest 2024（champion）

• Introduction: Track-2 focuses on mapping the water surface from Copernicus Sentinel-2 and Landsat optical imageries.
• Key words: Multi-spectral data, Flood rapid mapping

基于高分辨率可见光图像的感兴趣区域内部变化智能检测

• Introduction: 高分系列、资源3号系列卫星数据，分辨率2米，主要覆盖我国陆域范围内农用地及建设用地.

• Key words: SAR, Multi-model fusion, OHEM

高分辨率SAR图像中近海养殖场分割赛道决赛第六名

• Introduction: We propose an efficient solution to achieve the farm segmentation from SAR data.

• Key words: SAR, Multi-model fusion, OHEM

Learning Without Exact Guidance: Updating Large-scale High-resolution Land Cover Maps from Low-resolution Historical Labels

Zhuohong Li, Wei He, Jiepan Li, Fangxiao Lu, Hongyan Zhang

Conference on Computer Vision and Pattern Recognition (CVPR2024) (CCF-A)

Code

• Introduction: In this paper, we propose an efficient, weakly supervised framework (Paraformer) to guide large-scale HR land-cover mapping with easy-access historical land-cover data of low resolution (LR).
• Key words: Remote sensing, Landcover mapping, Weakly supervised, Semantic segmentation.

Change Guiding Network: Incorporating Change Prior to Guide Change Detection in Remote Sensing Imagery

C. Han, C. Wu, H. Guo, M. Hu, Jiepan Li, and H. Chen

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), 2023. (SCI Q2 TOP, IF=4.715)

Code

• Introduction: Our proposed hange guide module can effectively capture the long-distance dependency among pixels and overcomes the problem of the insufficient receptive field.
• Key words: Remote sensing, Change detection, Attention mechanism

C2F-SemiCD: A coarse-to-fine semi-supervised change detection method based on consistency regularization in High-Resolution Remote-Sensing Images

C. Han, C. Wu, M. Hu, Jiepan Li, and H. Chen

IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2024. (SCI Q1 TOP, IF=8.2)

Code

• Introduction: we propose a coarse-to-fine semi-supervised change detection method based on consistency regularization (C2F-SemiCD), which includes a coarse-to-fine change detection network with a multi-scale attention mechanism(C2FNet) and a semi-supervised update method.
• Key words: Remote sensing, Change detection, Semi-supervised