An uncertainty-aware evaluation framework based on hierarchical vision transformers for robust cross-domain plant leaf disease classification
Tripti Shrivastava, Ayush Kumar Agrawal, Abhinav Shukla, Parul Dubey · 2026
Read An uncertainty-aware evaluation framework based on hierarchical vision transformers for robust cross-domain plant leaf disease classification by Tripti Shrivastava, Ayush Kumar Agrawal, Abhinav Shukla, Parul Dubey (2026) 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-13447843.txt.
Description
Tripti Shrivastava and coauthors present a 2026 doubt-aware tool for plant leaf disease sorting that stays reliable when moving from lab to field images. Their layered vision model pairs multi-scale traits with Monte Carlo dropout doubt and heat tuning, tested both ways across lab and field data sets.
Scores reached 97.8 percent on lab data and 93.6 percent on field data, with tuning errors far below base conv and vision models. Domain-shift decay shrank and doubt conduct stayed stable. Farmers gain a field-use-ready spotting aid, though broader crop and region trials remain.
Catalog record
| CREATOR | Tripti Shrivastava, Ayush Kumar Agrawal, Abhinav Shukla, Parul Dubey |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 62 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |