IViT: An Incremental Learning Method for Object Detection of Hidden Hazards in Transmission Line Corridors
Min Li, Kun Fan, Peng Luo, Junping Liu · 2025
Read IViT: An Incremental Learning Method for Object Detection of Hidden Hazards in Transmission Line Corridors by Min Li, Kun Fan, Peng Luo, Junping Liu (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-12787700.txt.
Description
Min Li, Kun Fan, Peng Luo, and Junping Liu build a detector for hidden hazards along power line corridors, in a paper from 2025. The detector can learn new hazard types without full retraining. Drone checks spot most hazards, but fresh obstacle types keep showing up.
Their frame, IViT, blends a classic net with a transformer. A teaching trick passes old class knowledge to the new model. New blocks fuse wide and local views. On two test sets it beat main static and step wise detectors on key scores, in both first learning and later updates.
Catalog record
| CREATOR | Min Li, Kun Fan, Peng Luo, Junping Liu |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |