A Lightweight Transformer-Guided Model with Edge-Enhanced Preprocessing for Multi-Class Cassava Leaf Disease Detection
Bibliographic record
Abstract
Accurate detection of cassava leaf diseases is important to ensure crop health and sustainable agricultural productivity in resource-limited farming environments. This research work presents a compact hybrid model CassNet which is designed for the precise classification of different cassava leaf conditions. The proposed architecture combines a lightweight convolutional module with transformer network to efficiently capture detailed and contextual patterns. A coordinate attention mechanism is incorporated at multiple levels to highlight the disease-relevant regions and an edge-focused input enhancements are used to highlight the lesion boundaries and structural disruptions. The proposed model is evaluated on a labeled cassava leaf image dataset and the results exhibits the better classification accuracy of 93.28%, with precision, recall, and F1-score values of 0.9312, 0.9274, and 0.9293 respectively. The inference time was obtained as 18.4 ms per image which is significantly better than conventional CNN and transformer models. The proposed CassNet model provides a practical and deployable solution with minimal parameter load and high reliability across variable input conditions in real-time agricultural disease monitoring.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".