Deep learning for apple leaf disease diagnosis: a comparative study with convolutional neural networks and transformers
Soroush Toutounchian, Amirhosein Zobeiri, Alireza Rezaee, Farshid Hajati, Raymond Chiong · 2026
Read Deep learning for apple leaf disease diagnosis: a comparative study with convolutional neural networks and transformers by Soroush Toutounchian, Amirhosein Zobeiri, Alireza Rezaee, Farshid Hajati, Raymond Chiong (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-13438138.txt.
Description
Soroush Toutounchian's team compared deep learning models in 2026 for diagnosing apple leaf disease, a threat to yields and food security. Eight convolutional networks and two vision transformers were tuned with DropBlock regularization on a 2021 plant pathology image set covering five diseases plus healthy leaves, with thresholds later tuned by swarm optimization. A moderate DropBlock and dropout setting worked best.
Swin transformer variants led, reaching about ninety-one percent accuracy and the top F1 score, edging newer convolutional rivals. Orchard managers and plant pathologists get a ranked model comparison for fast, image-based diagnosis. Field photos with varied light and background will test whether lab accuracy survives the orchard.
Catalog record
| CREATOR | Soroush Toutounchian, Amirhosein Zobeiri, Alireza Rezaee, Farshid Hajati, Raymond Chiong |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 82 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |