Training Parameters for the ECL-RTDETR Rice Disease Detection Model

A small dataset of training parameters for the ECL-RTDETR model, an enhanced RT-DETR-based system for detecting rice diseases. The dataset was authored by Yaojun Zhang and last updated on June 3, 2026. It is a 5.5 KB XLS file shared under a CC-BY-4.0 license on figshare.

Use Cases

• Benchmarking lightweight vision model backbones based on the described EfficientViT architecture.
• Evaluating upsampling operators for feature preservation in agricultural image analysis, referencing the CARAFE operator.
• Studying adaptive feature learning in complex field conditions based on the LDConv module mentioned in the description.

Strengths

• Model performance metrics are provided in the description, including a 0.7% [email protected] improvement and a 22.2 FPS speed increase.
• The dataset is shared under a permissive CC-BY-4.0 license, facilitating reuse.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The description metadata is focused on the model; the specific content and structure of the parameter file are not detailed.

Provenance

Source

Yaojun Zhang via figshare.

Collection Method

Likely generated during the training of the ECL-RTDETR model described in the associated research.

Freshness

Last updated 2026-06-03 17:54:30; freshness should be verified.