Deep Learning for Cotton Disease Detection Lightweight, Explainable and Field-Ready Solutions
Bibliographic record
Abstract
Cotton is a crucial crop for the economy that is globally recognized as white gold and a major contributor to the Indian economy. However, cotton production is threatened due to various diseases affecting the leaves, like bacterial blight, leaf curl virus, fungal infections and pest attacks impacting the crop yield and quality that affect economic losses. The traditional disease detection methods, which depend on manual inspection, are inefficient, time-consuming, laborious, inaccurate and lead to misdiagnosis and often unreliable under field conditions. The need for early and accurate diagnosis is critical for timely intervention. In recent years Machine Learning (ML) and Deep Learning (DL) have been used for automated disease detection through leaf images. The study highlighted lightweight convolutional neural networks (CNNs), transformer-based models and object detection frameworks such as YOLO and RT-DETR, which have performed accurate results. Transfer learning with advanced backbones (EfficientNet, Xception, ResNet), integrating with attention mechanisms (e.g., CBAM, DFSA) for feature enrichment. The Explainable AI (XAI) for improving the explainability, while synthetic data generation using GANs reduces dataset imbalance. The review consolidated the current state of DL models for cotton disease detection, focusing on optimized approaches for mobile and edge deployment. Finally, it identifies existing research gaps and future directions for accurate, efficient, and field‑ready solutions.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".