Hybrid lightweight transformer for efficient landslide change detection in remote sensing imagery
Dhirendra Prasad Yadav, Bhisham Sharma, Shashank Singh, Panos Liatsis · 2025
Read Hybrid lightweight transformer for efficient landslide change detection in remote sensing imagery by Dhirendra Prasad Yadav, Bhisham Sharma, Shashank Singh, Panos Liatsis (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12808116.txt.
Description
Dhirendra Prasad Yadav, Bhisham Sharma, Shashank Singh, and Panos Liatsis present a hybrid lightweight transformer for landslide change detection in remote sensing images. Their 2025 paper designs a network to localize and segment landslide areas.
Convolutional networks extract only shallow spatial features and miss long-range dependencies, so landslide edges and boundaries are poorly covered. Their model, CDCTNet, pairs a lightweight convolutional encoder with transformer blocks. Local and global self-attention give context at two scales with little overhead. A decoder with convolution blocks and a gated attention block then produces the segmentation. The aim is accurate maps that stay cheap to run.
Catalog record
| CREATOR | Dhirendra Prasad Yadav, Bhisham Sharma, Shashank Singh, Panos Liatsis |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 80 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |