A method of deep network auto-training based on the MTPI auto-transfer learning and a reinforcement learning algorithm for vegetation detection in a dry thermal valley environment
Yayong Chen, Beibei Zhou, Chen Xiaopeng, Changkun Ma, Lei Cui, Feng Lei, Xiaojie Han, Linjie Chen, Shanshan Wu, Dapeng Ye · 2025
Read A method of deep network auto-training based on the MTPI auto-transfer learning and a reinforcement learning algorithm for vegetation detection in a dry thermal valley environment by Yayong Chen, Beibei Zhou, Chen Xiaopeng, Changkun Ma, Lei Cui, Feng Lei, Xiaojie Han, Linjie Chen, Shanshan Wu, Dapeng Ye (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-11864880.txt.
Description
Yayong Chen and co-authors present a self-training method for deep networks that spot plants in drone photos, in work from 2024. The setting is a dry, hot valley, where rough ground makes hand tuning slow and costly. Their method joins a transfer learning score with a sampling method that learns from rewards.
The transfer score finds fast start settings, so later rounds need only a small share of the data and time. The sampling method then grows the data set on its own and trims human error. Four network types were trained with the full method. The best one reached high scores on two accuracy measures. The authors offer the method as a way to cut hand work in field data tasks.
Catalog record
| CREATOR | Yayong Chen, Beibei Zhou, Chen Xiaopeng, Changkun Ma, Lei Cui, Feng Lei, Xiaojie Han, Linjie Chen, Shanshan Wu, Dapeng Ye |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |