In this article you will learn how the vision transformer works for image classification problems. We distill all the important details you need to grasp along with reasons it can work very well given enough data for pretraining.
How convolutional neural networks work? What are the principles behind designing one CNN architecture? How did we go from AlexNet to EfficientNet?
An intuitive understanding on Transformers and how they are used in Machine Translation. After analyzing all subcomponents one by one such as self-attention and positional encodings , we explain the principles behind the Encoder and Decoder and why Transformers work so well
What is transfer learning? How can it help us classify and segment different types of medical images? Are pretrained computer vision models useful for medical imaging tasks? How is 2D image classification different from 3D MRI segmentation in terms of transfer learning?
New to Natural Language Processing? This is the ultimate beginner’s guide to the attention mechanism and sequence learning to get you started
How can deep learning revolutionize medical image analysis beyond segmentation? In this article, we will see a couple of interesting applications in medical imaging such as medical image reconstruction, image synthesis, super-resolution, and registration in medical images
How can we efficiently train very deep neural network architectures? What are the best in-layer normalization options? We gathered all you need about normalization in transformers, recurrent neural nets, convolutional neural networks.
Learn how to apply 3D transformations for medical image preprocessing and augmentation, to setup your awesome deep learning pipeline
What are the advantages of RNN’s over transformers? When to use GRU’s over LSTM? What are the equations of GRU really mean? How to build a GRU cell in Pytorch?
Are you interested to see how recurrent networks process sequences under the hood? That’s what this article is all about. We are going to inspect and build our own custom LSTM model. Moreover, we make some comparisons between recurrent and convolutional modules, to maximize our understanding.
In this article, we dive into the state-of-the-art methods on self-supervised representation learning in computer vision, by carefully reviewing the fundamentals concepts of self-supervision on learning video representations.
Multiple introductory concepts regarding deep learning in medical imaging, such as coordinate system and dicom data extraction from the machine learning perspective.
An intuitive guide on why it is important to inspect the receptive field, as well as how the receptive field affect the design choices of deep convolutional networks.
The sixth article-series of GAN in computer vision - we explore semantic image synthesis and learning a generative model from a single image
The fifth article-series of GAN in computer vision - we discuss self-supervision in adversarial training for unconditional image generation as well as in-layer normalization and style incorporation in high-resolution image synthesis.