A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images

By Libo Wang, Rui Li, Chenxi Duan, Ce Zhang, Xiaoliang Meng, Shenghui Fang. IEEE Geoscience and Remote Sensing Letters, 2021

416 citations recorded by the source corpus.

The fully convolutional network (FCN) with an encoder-decoder architecture has been the standard paradigm for semantic segmentation. The encoder-decoder architecture utilizes an encoder to capture multilevel feature maps, which are incorporated into the final prediction by a decoder. As the context is crucial for precise segmentation, tremendous effort has been made to extract such information in an intelligent fashion, including employing dilated/atrous convolutions or inserting attention modules. However, these endeavors are all based on the FCN architecture with ResNet or other backbones, which cannot fully exploit the context from the theoretical concept. By contrast, we introduce the Swin Transformer as the backbone to extract the context information and design a novel decoder of densely connected feature aggregation module (DCFAM) to restore the resolution and produce the segmentation map. The experimental results on two remotely sensed semantic segmentation datasets demonstrate the effectiveness of the proposed scheme.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/a32a7879307d21a11b77f8e777042976da6b5b45

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Man On Pun
2. Xiaokang Zhang
3. Xianping Ma
4. Ming Liu
5. Ce Zhang
6. Rui Li
7. Libo Wang
8. Xiaoliang Meng

In Media Technology

1. Man On Pun
2. Xiaokang Zhang
3. Xianping Ma
4. Ming Liu
5. Ce Zhang
6. Rui Li
7. Libo Wang
8. Xiaoliang Meng

Citations in the corpus

• UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery (2021, positive): “The DC-Swin introduced Swin Transformer (Liu et al., 2021) as the encoder and designs a densely connected convolutional decoder for fine-resolution remote sensing image segmentation, surpassing the CNN-based methods by a large gap (Wang et al., 2022).”
• A Multilevel Multimodal Fusion Transformer for Remote Sensing Semantic Segmentation (2024, methodology): “Recently, deep learning (DL)-based methods have been successfully developed for remote sensing semantic segmentation by exploiting convolutional neural networks (CNNs) [14], [15], [16], [17], [18], [19], [20], [21], [22], [23], [24], [25].”