AWPF-ResNet18, a ResNet18-based model with an Adaptive Window Pyramid Fusion module, achieved performance improvements in edible mushroom classification tasks. The model's performance metrics, including accuracy, macro precision, macro F1-score, and macro recall, are documented in a 9.5 KB Excel file uploaded by Xinhai Zhao to figshare in April 2026. The dataset likely contains tabular results from comparative experiments validating the model's effectiveness.
Use Cases
- Benchmarking image classification models based on reported accuracy, precision, F1-score, and recall metrics
- Evaluating feature fusion techniques for mitigating semantic information loss during downsampling
- Comparing model performance on tasks involving targets of varying sizes within images
Strengths
- Performance metrics show specific improvements: accuracy increased by 2.5%, macro precision by 7.5%, macro F1-score by 5%, and macro recall by 2%
- Dataset is openly licensed under CC-BY-4.0
Limitations
- Dataset size is only 9.5 KB, indicating a very limited scope of data
- Row count and column-level documentation are unknown; field semantics must be inferred after download
- Description metadata is limited; actual data quality requires manual inspection after download
Provenance
- Source
- figshare
- Collection Method
- Likely contains experimental results from comparative validation tests of the AWPF-ResNet18 model.
- Freshness
- Last updated 2026-04-16 17:31:45; freshness should be verified