mit-b3

Model overview

mit-b3 is published by nvidia as a SegFormer image-classification model. The captured configuration identifies SegformerForImageClassification with model type segformer. According to the model card, it is a b3-sized encoder fine-tuned on ImageNet-1k and introduced in the SegFormer paper by Xie et al. The card notes it was written by the Hugging Face team, not the team releasing SegFormer.

Recorded capabilities

Use cases in the source record

• Encoder fine-tuning workflows using the repository's pre-trained hierarchical Transformer.
• Image classification into one of the 1,000 ImageNet classes using the card's documented Transformers feature-extractor workflow.

Limitations and unknowns

• No parameter count was extracted from this record.
• No evaluation results were extracted from this record.
• The hub license value is other; the model card points to an external license reference whose full terms were not extracted.
• Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: nvidia/mit-b3

Captured: Unknown. Processed: 2026-09-07T19:34:54.069375+00:00.

SegFormer (b3-sized) encoder pre-trained-only SegFormer encoder fine-tuned on Imagenet-1k. It was introduced in the paper SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers by Xie et al. and first released in this repository . Disclaimer: The team releasing SegFormer did not write a model card for this model so this model card has been written by the Hugging Face team. Model description SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmentation benchmarks such as ADE20K and Cityscapes. The hierarchical Transformer is…