Segformer B2 Finetuned Ade 512 512
SegFormer is a hierarchical Transformer encoder with a lightweight all-MLP decoder for semantic segmentation, built by researchers and released by NVIDIA. It is fine-tuned specifically on the ADE20k dataset at a resolution of 512x512. A notable technical trait is its encoder is pre-trained on ImageNet-1k before the decoder is added and the whole system is fine-tuned.
Input
Output
Context
-
Max Output
-
Parameters
-
Technical Specifications
Model TypeVision
Context WindowNot available
Max Output TokensNot available
ParametersNot available
Release DateMar 2, 2022
Training CutoffNot available
Licenseother
Open SourceYes
Input Modalities
Image
Output Modalities
Image
Capabilities
Resources & Links
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.