Projects

latest | popular

Filter by
Learning Representations via Graph-structured Networks
Introduce a series of effective graph-structured networks, including non-local neural networks, spatial generalized propagation networks, etc.
graph-neural-networks graph-structured-networks non-local-neural-networks spatial-generalized-propagation-networks
A Few Favorite Recipes in Computer Vision & Deep Learning
This blog post enlists a few of my favorite recipes in deep learning in the context of computer vision (as of August 2020).
self-supervised-learning simclr contrastive-learning representation-learning
Extracting Structured Data from Templatic Documents
Automatically extract data from structured documents—invoices, receipts, etc.—with the potential to streamline many business workflows.
structured-data representation-learning tables templatic-documents
Supervised Contrastive Learning
Implements the ideas presented in Supervised Contrastive Learning (https://arxiv.org/pdf/2004.11362v1.pdf) by Khosla et al.
deep-learning representation-learning contrastive-learning supervised-contrastive-learning
SimCLR in TensorFlow 2
(Minimally) implements SimCLR (https://arxiv.org/abs/2002.05709) in TensorFlow 2.
self-supervised-learning representation-learning deep-learning computer-vision
Self-Supervised Representation Learning
What if we can get labels for free for unlabelled data and train unsupervised dataset in a supervised manner?
self-supervised-learning representation-learning generative-modeling object-recognition
Evolution of Representations in the Transformer
The evolution of representations of individual tokens in Transformers trained with different training objectives (MT, LM, MLM - BERT-style).
transformers representation-learning representations natural-language-processing
Motion2Vec
Semi-Supervised Representation Learning from Surgical Videos
motion-estimation semi-supervised-learning representation-learning surgery
projects 1 - 10 of 38
Topic experts
Share a project
Share something you or the community has made with ML.