KieDani/SegformerPlusPlus
Official implementation of "Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic Segmentation
This project helps computer vision practitioners accelerate the processing of high-resolution images for tasks like identifying objects in street scenes or pinpointing human body parts. It takes existing deep learning models and optimizes them to process images faster while maintaining accuracy. This is ideal for researchers or developers working with real-time image analysis or deploying models on devices with limited computing power.
Use this if you need to perform semantic segmentation or human pose estimation on high-resolution images and require faster inference or more efficient training with reduced memory usage.
Not ideal if your primary concern is achieving the absolute highest accuracy without any regard for processing speed or memory consumption.
Stars
26
Forks
2
Language
Python
License
GPL-3.0
Category
Last pushed
Dec 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/KieDani/SegformerPlusPlus"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
WangLibo1995/GeoSeg
UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban...
cvjena/cn24
Convolutional (Patch) Networks for Semantic Segmentation
TUI-NICR/EMSANet
EMSANet: Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments
qizhuli/Weakly-Supervised-Panoptic-Segmentation
Weakly- and Semi-Supervised Panoptic Segmentation (ECCV18)
ManuelPalermo/AndroidVideoSegmentation
Android video semantic segmentation using DeeplabV3+ lite