nvidia / image-segmentation Open weights updated 4 years ago

segformer-b2-finetuned-ade-512-512

Name: segformer-b2-finetuned-ade-512-512
Author: nvidia

SegFormer model fine-tuned on ADE20k at resolution 512x512. 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.

Params

—

Context

—

Downloads 30d

187 K

Likes

Licence: other Not gated View on Hugging Face ↗

Download history

daily snapshots · 106 days

▲ 72 K in the last 30 days (27.8%)

366 K187 K

Jul 28Sep 1Oct 6Nov 10

Specifications

Architecture: SegformerForSemanticSegmentation
Licence: other
First seen on the Hub: 2022-03-02
Training datasets: scene_parse_150
Added to our catalog: 2026-07-28

Compare with any image-segmentation model

Popular comparisons

BiRefNet 1.0 M clipseg-rd64-refined 437 K segformer_b2_clothes 434 K RMBG-2.0 408 K mask2former-swin-large-ade-semantic 336 K mask2former-swin-large-cityscapes-semantic 230 K