Deep Learning Backbone Performance Comparison on FMA-Medium Music Dataset

A 5.5 KB Excel file by Yunyan Ma, last updated in April 2026, compares the performance of various deep learning backbones and a proposed method on the FMA-Medium music dataset. The dataset likely contains tabular results from model evaluations. It is hosted on figshare under a CC-BY-4.0 license.

Use Cases

• Benchmarking deep learning architectures based on performance metrics on the FMA-Medium dataset
• Comparing a proposed method against established backbones based on the described evaluation
• Informing model selection for music classification or analysis tasks based on comparative results

Strengths

• File size is precisely 5.5 KB, indicating a compact and focused dataset
• Has a clear, permissive license (CC-BY-4.0) for reuse
• Provides a specific, recent update timestamp (2026-04-09)

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download
• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment

Provenance

Source

figshare, author Yunyan Ma

Collection Method

Likely contains results from computational experiments comparing deep learning models.

Time Range

Dataset last updated in 2026; temporal coverage of the underlying FMA-Medium data is unknown.

Freshness

Last updated 2026-04 09 17:38:03; freshness should be verified

Geography

Spatial coverage is not specified.