1 code implementation • 18 Sep 2021 • Libo Wang, Rui Li, Ce Zhang, Shenghui Fang, Chenxi Duan, Xiaoliang Meng, Peter M. Atkinson
In this paper, we propose a Transformer-based decoder and construct a UNet-like Transformer (UNetFormer) for real-time urban scene segmentation.
Ranked #1 on Scene Segmentation on UAVid
1 code implementation • 23 Jun 2021 • Libo Wang, Rui Li, Dongzhi Wang, Chenxi Duan, Teng Wang, Xiaoliang Meng
Specifically, the dependency path is conducted based on the ResT, a novel Transformer backbone with memory-efficient multi-head self-attention, while the texture path is built on the stacked convolution operation.
Ranked #4 on Semantic Segmentation on UAVid
1 code implementation • IEEE Transactions on Geoscience and Remote Sensing 2021 • Rui Li, Shunyi Zheng, Ce Zhang, Chenxi Duan, Jianlin Su, Libo Wang, Peter M. Atkinson
A novel attention mechanism of kernel attention with linear complexity is proposed to alleviate the large computational demand in attention.
Ranked #7 on Semantic Segmentation on ISPRS Vaihingen
1 code implementation • 25 Apr 2021 • Libo Wang, Rui Li, Chenxi Duan, Ce Zhang, Xiaoliang Meng, Shenghui Fang
The fully convolutional network (FCN) with an encoder-decoder architecture has been the standard paradigm for semantic segmentation.
Ranked #3 on Semantic Segmentation on ISPRS Potsdam (using extra training data)
no code implementations • 14 Mar 2021 • Libo Wang, Ce Zhang, Rui Li, Chenxi Duan, Xiaoliang Meng, Peter M. Atkinson
However, MSR images suffer from two critical issues: 1) increased scale variation of geo-objects and 2) loss of detailed information at coarse spatial resolutions.
2 code implementations • 16 Feb 2021 • Rui Li, Shunyi Zheng, Ce Zhang, Chenxi Duan, Libo Wang
Based on FPN and AAM, a novel framework named Attention Aggregation Feature Pyramid Network (A2-FPN) is developed for semantic segmentation of fine-resolution remotely sensed images.
1 code implementation • 4 Feb 2021 • Rui Li, Chenxi Duan
Specifically, the high-caliber performance of the convolutional neural network (CNN) heavily relies on fine-grained spatial details (fine resolution) and sufficient contextual information (large receptive fields), both of which trigger high computational costs.
Ranked #5 on Semantic Segmentation on UAVid
no code implementations • 20 Dec 2020 • Chenxi Duan, Rui Li
In remote sensing images, the existence of the thin cloud is an inevitable and ubiquitous phenomenon that crucially reduces the quality of imageries and limits the scenarios of application.
1 code implementation • 29 Nov 2020 • Rui Li, Shunyi Zheng, Chenxi Duan, Jianlin Su, Ce Zhang
The attention mechanism can refine the extracted feature maps and boost the classification performance of the deep network, which has become an essential technique in computer vision and natural language processing.
no code implementations • 3 Sep 2020 • Rui Li, Shunyi Zheng, Chenxi Duan, Ce Zhang, Jianlin Su, P. M. Atkinson
A novel attention mechanism of kernel attention with linear complexity is proposed to alleviate the large computational demand in attention.
no code implementations • 11 Aug 2020 • Chenxi Duan, Jun Pan, Rui Li
In this paper, a novel thick cloud removal method for remote sensing images based on temporal smoothness and sparsity-regularized tensor optimization (TSSTO) is proposed.
1 code implementation • 1 Aug 2020 • Rui Li, Shunyi Zheng, Chenxi Duan, Ce Zhang
In this paper, a Multi-Scale Fully Convolutional Network (MSFCN) with multi-scale convolutional kernel is proposed to exploit discriminative representations from two-dimensional (2D) satellite images.
2 code implementations • 29 Jul 2020 • Rui Li, Jianlin Su, Chenxi Duan, Shunyi Zheng
In this paper, to remedy this deficiency, we propose a Linear Attention Mechanism which is approximate to dot-product attention with much less memory and computational costs.
2 code implementations • 26 Jul 2020 • Rui Li, Chenxi Duan, Shunyi Zheng, Ce Zhang, Peter M. Atkinson
In this Letter, we incorporate multi-scale features generated by different layers of U-Net and design a multi-scale skip connected and asymmetric-convolution-based U-Net (MACU-Net), for segmentation using fine-resolution remotely sensed images.
no code implementations • 17 Apr 2020 • Rui Li, Chenxi Duan
Hyperspectral Image (HSI) classification based on deep learning has been an attractive area in recent years.