Abstract: SuperpixelGridMasks. It is a data augmentation approach which permits to generate various complementary images from original sensor-based data of varied natures e.g. X-Ray scans, vehicular scenes, people images (see data samples). This approach allows to increase the size of your image-based training datasets towards expecting better performances in your analysis tasks. Experiments have shown that the approach can be efficient for image classification tasks.

Link: https://www.researchgate.net/publication/360062941_SuperpixelGridCut_SuperpixelGridMean_and_SuperpixelGridMix_Data_Augmentation
@Machine_learn

FastFold: Reducing AlphaFold Training Time from 11 Days to 67 Hours

Github: https://github.com/hpcaitech/fastfold

Paper: https://arxiv.org/abs/2203.00854v1

@Machine_learn

Uncertainty Estimation for Heatmap-based Landmark Localization

Github: https://github.com/pykale/pykale

Documentatuin: https://github.com/pykale/pykale

Paper: https://arxiv.org/abs/2203.02351v1

Dataset: https://paperswithcode.com/dataset/kitti

@Machine_learn

https://web.njit.edu/~ym329/dlg_book/dlg_book.pdf

Deep Learning on Graphs

📖 Book

#deeplearning #DL

@Machine_learn

Cryptocurrency liquidity and volatility interrelationships during
the COVID-19 pandemic #Paper @Machine_learn

Periodicity in Cryptocurrency Volatility and Liquidity #Paper @Machine_learn

Deep residual learning for image recognition #paper
@Machine_learn

Alpa: Automated Model-Parallel Deep Learning


http://ai.googleblog.com/2022/05/alpa-automated-model-parallel-deep.html

@Machine_learn

Pix2Seq: A New Language Interface for Object Detection


http://ai.googleblog.com/2022/04/pix2seq-new-language-interface-for.html

@Machine_learn

🔎 Cross-view Transformers for real-time Map-view Semantic Segmentation

Code: https://github.com/bradyz/cross_view_transformers

Paper: https://arxiv.org/abs/2205.02833v1

Dataset: https://paperswithcode.com/dataset/nuscenes

@Machine_learn

Predicting academic performance by considering student heterogeneity #Paper @Machine_learn

An Introduction to Neural
Networks and Deep Learning #Chapter1 @Machine_learn

An Introduction to Deep
Convolutional Neural Nets for
Computer Vision #Chapter2 @Machine_learn

Multi-Instance Multi-Stage
Deep Learning for Medical
Image Recognition #Chapter4 @Machine_learn

Automatic Interpretation of
Carotid Intima–Media
Thickness Videos Using
Convolutional Neural
Networks #Chapter5 @Machine_learn

Deep Cascaded Networks for
Sparsely Distributed Object
Detection from Medical
Images #Chapter6 @Machine_learn

Deep Voting and Structured
Regression for Microscopy
Image Analysis #Chapter7 @Machine_learn