C-MAN: A Multi-attention Approach for Precise Plant Species Classification and Disease Detection Using Multi-scale, Channel-Wise, and Cross-Modal Attentions
Bibliographic record
Abstract
Accurate plant leaf detection and disease diagnosis are crucial for various applications, including plant species identification, disease management, and ecological monitoring.Existing methods often rely on single modalities, limiting their effectiveness due to insufficient spatial resolution, sensitivity, and disease-specific features.To overcome these limitations, we propose a novel approach C-MAN using multi-attention networks with multi-scale, channel-wise, and cross-modal attention mechanisms for plant leaf analysis and disease diagnosis.Multi-Scale Attention captures both fine-grained and global features, ensuring comprehensive understanding of leaf shape, texture, and disease patterns.Channelwise Attention focuses on disease-specific information within each feature channel, enhancing disease detection sensitivity.Cross-modal Attention integrates information from various weighted feature maps for richer and more robust analysis.We train our model on a standard plant leaf dataset of 4,500 images from twelve economically and environmentally significant plant species, containing both healthy and diseased leaves.The model performs a two-step categorization, first classifying leaves by species and then diagnosing diseases.We evaluate our approach using standard metrics like accuracy, precision, recall, and F1score.Our experiments demonstrate significant improvements in plant detection accuracy (96.74%) and disease diagnosis accuracy (95.43%) compared to single-modal methods.These results highlight the potential of our approach for more reliable and accurate plant analysis in various domains.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 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".