Focal-Transformer
by microsoft
[NeurIPS 2021 Spotlight] Official code for "Focal Self-attention for Local-Global Interactions in Vision Transformers"
AI summary
Attention-based transformer
A vision transformer architecture that uses a novel attention mechanism to capture local-global interactions in images
- stars
- 547
- forks
- 60
- watching
- 16
- awesome list
- 1
Similar projects
Found by comparing what the projects do, not just their names.
Vision Transformer
An implementation of a transformer-based vision model that aggregates local transformers on image blocks to improve accuracy and efficiency.
Translation model
Implementation of a transformer-based translation model in PyTorch
Attention library
Provides primitives for sparse attention mechanisms used in transformer models to improve computational efficiency and scalability
Image encoder
An implementation of a vision transformer architecture designed for high-resolution image encoding with multiple efficient attention mechanisms
View transformer
This project focuses on manipulating 3D views using deep learning techniques.
Object attention framework
A PyTorch implementation of an attention-guided inference network to focus on specific areas of objects in images
Transformer toolkit
Provides a collection of reusable data transformation tools
Transformer trainer
Research tool for training large transformer language models at scale
Feature transformer
A Python library with multiple transformers to engineer and select features for use in machine learning models.
gabeur/mmt259
Video retriever
Develops a cross-modal architecture for video retrieval by combining multiple types of features from videos and text
Scene Text Recognizer
A deep learning framework for scene text recognition with rectification and attention mechanisms.
Deblurring model
A PyTorch implementation of an attention network for dynamic scene deblurring
Network architectures
A collection of modern neural network architectures for computer vision tasks that don't use self-attention mechanisms.
Text-to-image generator
Develops a PyTorch model for 4K text-to-image generation using diffusion transformer
Vision Transformer
A PyTorch implementation of the Vision Transformer model for image recognition tasks.
Featured in 1 awesome list
Each link jumps to the spot where the list mentions Focal-Transformer.
