Research-notes

In this article, I'm sharing my method to read 1 paper per day.

Old paper but since there was some breakthrough in self-supervised learning, I'm studying deeper this topic recently.

Great paper! Very pragmatic and it works well!

Other notes that I took from the papers I read for my project in Medical Image Segmentation. It's not a variation of UNet.

I'm currently working on a biomedical 2D image segmentation project so I'm reading all related papers. I took some notes and here is the first of the series. UNet, a very popular architecture.

A common limitation or pain point in a project involving machine learning is the amount of annotated data needed to train our models. In this paper, the authors are exploring what they call Contrastive Predictive Coding. This method allows their models to learn representations (features) in an unsupervised manner. In the end, the goal is to provide a training process that would require much less annotated data.

This paper was published by Mingxing Tan and Quoc V. Le, members of Google Research, Brain Team. They propose a method to scale up neural nets. Their biggest model achieves **84.4% top-1 / 97.1% top-5 accuracy on ImageNet** and the state-of-the-art on CIFAR-100, while being **8.4x smaller and 6.1x faster on inference** than the best existing ConvNet.

This paper introduces several tricks that can significantly improve the accuracy of common models. And those tricks are quite easy to implement. Here are my notes.