Ablation Study Results for Semantic Segmentation Datasets

Comprising ablation study results measuring mIoU (%) for the Potsdam, Vaihingen, UAVid, and MSIDBG remote sensing image datasets. The data is provided in an XLS file with a size of 5.5 KB. It was authored by Xin Wang and last updated in March 2026.

Use Cases

• Compare mIoU performance across the Potsdam, Vaihingen, UAVid, and MSIDBG datasets to evaluate model generalization.
• Analyze the effect of weight α on mIoU for semantic segmentation tasks involving dense small targets and complex boundary shapes.
• Benchmark semantic segmentation network performance on remote sensing images with wide imaging ranges and varying resolution detail features.

Strengths

• Data is recent, with a last update timestamp of March 2026.
• The dataset covers results from four distinct remote sensing datasets (Potsdam, Vaihingen, UAVid, MSIDBG).
• It is shared under a permissive CC BY 4.0 license.

Limitations

• The dataset is very small at 5.5 KB, indicating limited scope and likely a summary of results rather than raw data.
• No column definitions or sample data are available, limiting understanding of the data structure.
• The row count is unknown, making it difficult to assess the volume of experimental results.

Provenance

Source

figshare, authored by Xin Wang.

Collection Method

Results from an ablation study on semantic segmentation models.

Freshness

Last updated March 2026.

Geography

Covers datasets with imagery from Potsdam, Vaihingen, and other unspecified locations (UAVid, MSIDBG).