nested-transformer

Vision Transformer

An implementation of a transformer-based vision model that aggregates local transformers on image blocks to improve accuracy and efficiency.

Nested Hierarchical Transformer https://arxiv.org/pdf/2105.12723.pdf

GitHub

195 stars
8 watching
26 forks
Language: Jupyter Notebook
last commit: about 2 years ago
Linked from 1 awesome list

imagenettransformervision

Backlinks from these awesome lists:

Related projects:

RepositoryDescriptionStars
jeonsworld/vit-pytorchA PyTorch implementation of the Vision Transformer model for image recognition tasks.1,959
lahoud/3d-vision-transformersCompiles and shares 3D computer vision papers using transformer models409
dirtyharrylyl/transformer-in-visionA collection of resources and papers related to Transformer-based computer vision models and techniques.1,324
microsoft/focal-transformerA vision transformer architecture that uses a novel attention mechanism to capture local-global interactions in images547
google-research/vision_transformerProvides pre-trained models and code for training vision transformers and mixers using JAX/Flax10,620
yitu-opensource/t2t-vitA deep learning framework for training vision transformers from scratch on image data.1,162
zhoudaquan/dvit_repoAn implementation of Deep Vision Transformer models with modifications to improve performance by preventing attention collapse137
whai362/pvtAn implementation of Pyramid Vision Transformers for image classification, object detection, and semantic segmentation tasks1,745
lucidrains/reformer-pytorchAn implementation of Reformer, an efficient Transformer model for natural language processing tasks.2,132
gordonhu608/mqt-llavaA vision-language model that uses a query transformer to encode images as visual tokens and allows flexible choice of the number of visual tokens.101
gamrix/cs231n_projThis project focuses on manipulating 3D views using deep learning techniques.6
zsdonghao/spatial-transformer-netsAn implementation of Spatial Transformer Networks in TensorFlow for learning to apply transformations to images via classification tasks.36
josejuanqm/odyAn image generator that applies various transformations and styles to images45
ibrahimsobh/transformersAn implementation of deep neural network architectures, including Transformers, in Python.214
matlab-deep-learning/transformer-modelsAn implementation of deep learning transformer models in MATLAB209