EfficientNet-CBAM-prototype: an attention-guided EfficientNet framework with dynamic prototype representation for tomato disease classification
E Jansi, Kavitha BR · 2026
Read EfficientNet-CBAM-prototype: an attention-guided EfficientNet framework with dynamic prototype representation for tomato disease classification by E Jansi, Kavitha BR (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-13601356.txt.
Description
Jansi and Kavitha present a deep learning system in a 2026 paper for sorting tomato plant diseases from leaf images. Early, exact diagnosis matters because a delay of days can cost a crop. Standard image networks struggle with fine symptom detail, mix up look alike diseases, and can be hard to train when attention parts start from scratch.
Their system joins an efficient image backbone with an attention module that reweights features by channel and space. A memory layer keeps a moving prototype for each disease class and sorts new images by likeness to those prototypes. A two phase plan freezes the attention module first to steady training. The design targets field ready tools for growers.
Catalog record
| CREATOR | E Jansi, Kavitha BR |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 72 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |