maggiesong7/FullyAttentional
Fully Attentional Network for Semantic Segmentation [AAAI 2022]
This helps researchers in computer vision accurately outline distinct objects and regions within images. It takes an image as input and outputs a detailed, pixel-level classification of what each part of the image represents, even for small or inconsistently shaped objects. It's designed for computer vision scientists and engineers working on image understanding.
No commits in the last 6 months.
Use this if you need highly precise object outlining and classification within images, especially when dealing with complex scenes or small and thin objects.
Not ideal if your primary goal is general object detection or classification without needing a pixel-by-pixel segmentation map.
Stars
25
Forks
1
Language
Python
License
MIT
Last pushed
Aug 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/maggiesong7/FullyAttentional"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
qubvel-org/segmentation_models.pytorch
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
tue-mps/eomt
[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).
OSUPCVLab/SegFormer3D
Official Implementation of SegFormer3D: an Efficient Transformer for 3D Medical Image...
jeya-maria-jose/Medical-Transformer
Official Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image...
davidiommi/Pytorch--3D-Medical-Images-Segmentation--SALMON
Segmentation deep learning ALgorithm based on MONai toolbox: single and multi-label segmentation...