upernet-swin-tiny

Model overview

upernet-swin-tiny is published by openmmlab for image segmentation. The captured configuration identifies UperNetForSemanticSegmentation with model type upernet, and card data records MIT licensing. According to the model card, it applies the UperNet framework with a tiny-sized Swin Transformer backbone.

Recorded capabilities

Use cases in the source record

• Semantic-segmentation work using the publisher-described UperNet backbone, FPN, and Pyramid Pooling Module structure.
• Scene-parsing experiments following the publisher-cited UperNet and Swin Transformer papers.

Limitations and unknowns

• No Safetensors parameter count was captured for this record.
• No evaluation results were extracted from this record.
• Provider state is historical snapshot data and should be refreshed before being presented as current.
• Descriptive detail comes from a Hugging Face team-written card rather than the releasing team.

Source and provenance

Source: openmmlab/upernet-swin-tiny

Captured: Unknown. Processed: 2026-09-07T19:34:54.362905+00:00.

UperNet, Swin Transformer tiny-sized backbone UperNet framework for semantic segmentation, leveraging a Swin Transformer backbone. UperNet was introduced in the paper Unified Perceptual Parsing for Scene Understanding by Xiao et al. Combining UperNet with a Swin Transformer backbone was introduced in the paper Swin Transformer: Hierarchical Vision Transformer using Shifted Windows . Disclaimer: The team releasing UperNet + Swin Transformer did not write a model card for this model so this model card has been written by the Hugging Face team. Model description UperNet is a framework for semantic segmentation. It consists of several c…