EdgeCaseDNet: An enhanced detection architecture for edge case perception in autonomous driving
Yin Lei, Chen Shan, Wancheng Ge, Alessio Plebe, Alessio Plebe, Alessio Plebe, Alessio Plebe · 2025
Read EdgeCaseDNet: An enhanced detection architecture for edge case perception in autonomous driving by Yin Lei, Chen Shan, Wancheng Ge, Alessio Plebe, Alessio Plebe, Alessio Plebe, Alessio Plebe (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-12714283.txt.
Description
Yin Lei, Chen Shan, and Wancheng Ge present a vision system tuned for rare, hard cases in self-driving in a 2025 paper. Normal test sets underplay fog, rain, snow, and night driving, where detection can fail badly. The team built both a new dataset of such edge cases and a model designed to handle them.
Their model extends a popular detector with four upgrades, covering feature extraction, multi-scale fusion, a leaner convolution block, and a better training loss. On their tests it beat the base model by wide margins on standard accuracy scores. Code is shared online. The work targets the long tail of road scenes where safety margins are thinnest.
Catalog record
| CREATOR | Yin Lei, Chen Shan, Wancheng Ge, Alessio Plebe, Alessio Plebe, Alessio Plebe, Alessio Plebe |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 68 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |