Ablation Study Results for Optimizer Selection in Cocoa Pod Disease Detection

Ablation study results for a novel deep learning model applied to cocoa pod disease classification. The dataset, 5.5 KB in size, was authored by Henry Techie-Menson and last updated on April 30, 2026. It contains results from evaluating a Learnable Gated Fusion Convolutional Block Attention Module (LGF-CBAM) integrated with a ResNetV2-101 backbone.

Use Cases

• Benchmarking new attention mechanisms for plant disease classification based on the described LGF-CBAM architecture.
• Analyzing model generalization performance based on cross-dataset evaluation results mentioned in the description.
• Comparing optimizer performance for deep learning models in agricultural image analysis based on the study's title.

Strengths

• Model achieved a reported 98.95% accuracy on the primary Cocoa_Pod_Disease_Gh dataset.
• Cross-dataset evaluation demonstrated robustness with accuracies ranging from 96.19% to 98.53% on three other datasets.
• Dataset is openly shared under a CC-BY-4.0 license.

Limitations

• The dataset is very small at 5.5 KB, suggesting it contains summary results rather than raw image data.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

Henry Techie-Menson via figshare

Collection Method

Likely contains experimental results from training and evaluating a deep learning model.

Freshness

Last updated 2026-04-30 17:51:54; freshness should be verified.