GOKULPRASANTH-M/ViMbaFormer-A-Hybrid-Vision-Mamba-Unet-Architecture-for-UAV-Semantic-Segmentation
ViMbaFormer is a hybrid semantic segmentation framework designed for high-resolution UAV imagery. It integrates Vision Transformers, Mamba State Space Models, and a U-Net–style encoder–decoder to jointly model global context and fine spatial details with linear-time complexity.
Stars
—
Forks
—
Language
—
License
—
Category
Last pushed
Feb 06, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/GOKULPRASANTH-M/ViMbaFormer-A-Hybrid-Vision-Mamba-Unet-Architecture-for-UAV-Semantic-Segmentation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MLSTRUCT/MLStructFP
Multi-unit floor plan dataset for architectural analysis and recognition
rankseg/rankseg
Boost segmentation model mIoU/Dice instantly WITHOUT retraining. A plug-and-play, training-free...
fregu856/deeplabv3
PyTorch implementation of DeepLabV3, trained on the Cityscapes dataset.
DrSleep/light-weight-refinenet
Light-Weight RefineNet for Real-Time Semantic Segmentation
zijundeng/pytorch-semantic-segmentation
PyTorch for Semantic Segmentation