mit-b0

Model overview

mit-b0 is published by nvidia as a segformer-based image-classification model. The captured configuration identifies SegformerForImageClassification. According to the model card, it is a SegFormer b0-sized encoder finetuned on ImageNet-1k, with a hierarchical Transformer plus lightweight all-MLP decode-head design.

Recorded capabilities

Use cases in the source record

• ImageNet 1,000-class classification experiments using the card's documented Transformers workflow.
• Fine-tuning starting points for vision work using the publisher-described pretrained hierarchical Transformer.

Limitations and unknowns

• No parameter count was extracted from this record.
• No evaluation results were extracted from this record.
• The card notes it was written by the Hugging Face team because the releasing team did not provide one, so publisher attribution should be treated with care.
• Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: nvidia/mit-b0

Captured: Unknown. Processed: 2026-09-07T19:34:54.957119+00:00.

SegFormer (b0-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…