WaveletHSI: Direct HSI Classification from Compressed Wavelet Coefficients via Sub-Band Feature Extraction and Fusion
Xin Li, Baile Sun, Jacques Blanc-Talon, Patrice Delmas · 2025
Read WaveletHSI: Direct HSI Classification from Compressed Wavelet Coefficients via Sub-Band Feature Extraction and Fusion by Xin Li, Baile Sun, Jacques Blanc-Talon, Patrice Delmas (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-12733817.txt.
Description
Xin Li and co-authors built a tool that sorts rich color images without first unpacking them in a 2025 paper. Such images hold far more color bands than a normal photo, and the unpack step is a heavy cost. They are stored in a wavelet packed form, so the team taught a network to read that packed form as it stands.
Their frame pulls traits from each wavelet band in its own branch, then fuses them with a flipped form of attention. Sharp detail bands ask the questions, and dense base bands supply the answers. On three test sets the scores matched top unpack first tools, while the unpack cost fell by more than half.
Catalog record
| CREATOR | Xin Li, Baile Sun, Jacques Blanc-Talon, Patrice Delmas |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 66 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |