Fantastic Beasts

Fantastic Beasts is a dataset collected for the NeurIPS 2023 paper 'AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation'. It was created by author chaofanma and last updated on Hugging Face in October 2025. The dataset is designed to address the lack of rare or obscure vocabulary in existing segmentation benchmarks.

Use Cases

• Benchmarking open-vocabulary semantic segmentation models based on the attribute decomposition-aggregation method.
• Training models to segment images containing rare or obscure object categories mentioned in the description.
• Researching attribute-based reasoning for zero-shot image classification and segmentation.

Strengths

• Dataset is associated with a peer-reviewed NeurIPS 2023 paper, suggesting a research-grade benchmark.
• Last updated on 2025 10 25 12:59:50, indicating recent maintenance on the platform.

Limitations

• Row count, file formats, and dataset size are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• License information is unavailable, which may restrict usage.

Provenance

Source

Hugging Face dataset repository by author chaofanma.

Collection Method

Collected for the NeurIPS 2023 paper 'AttrSeg'.

Time Range

null

Freshness

Last updated 2025-10-25 12:59:50

Geography

null