How using self-attention for image classification reduces inductive bias inherent to CNNs including translation equivariance and locality, thus improving performance compared to ResNets when pre-trained with much larger datasets such as ImageNet-21k — *This post’s associated Colab Notebook contains step-by-step code for downloading pre-trained ViT model checkpoints, defining a model instance, and fine-tuning ViT.

Optimizing domain adaptation through toggling data annotation, training frameworks, and pre-training datasets — In this post, I will introduce the concept of domain adaptation in machine learning and discuss the process of optimizing Adversarial Discriminative Domain Adaptation (ADDA) framework. Here is the table of contents: Motivation for Domain Adaptation — Domain Shift Goal of Domain Adaptation — Semantic Alignment

How to ask CNN architectures useful questions to get insights about their behaviours — **Edit on February 10, 2020 : I have released an open-source library for visualization tools covered in this post using PyTorch, which you can install with pip install FeatureMapVisualizer. You can also check out: Colab notebook example (step-by-step instructions) Github repository PyPi page for FeatureMapVisualizer package

How can we adjust input data and labels to encourage neural networks to “perceive” images flexibly as humans do? — Flexibility of Human Perception 👼 Since we were little, we have learned about the world by observing and interacting with diverse stimuli through our five senses. Human perception involves continuous naming, characterizing, and remembering things in the environment while referring to the database of “what I know”. If I see something close to a particular…

t-SNE Plots as a means of communicating with a deep learning model — History : For my masters research project at University of Toronto, I was given airport Xray baggage scan images containing gun and knife to develop a model that performs an automatic detection of gun and knife in the baggage. …

Thinking about the Procedure >> Following the Procedure — When solving a machine learning problem, a common practice is to first search for a widely-accepted procedure (if any) for the problem. While following that procedure, it’s important to constantly review if things are on the right track and analyze the results both mathematically and intuitively. In other words, it’s…

Seed of Thought : Just how much about the ML model do we know after looking at the confusion matrix? — Background: I’m sharing my computer vision research project conducted during ML masters at University of Toronto. I was given Xray baggage scan images by an airport to develop a model that performs automatic detection of dangerous objects (gun and knife). …

How to creatively design data for your ML problem — Background: I’m sharing my computer vision research project experience for my masters degree in machine learning at University of Toronto. I was given Xray baggage scan images by an airport to develop a model that performs automatic detection of dangerous objects. …

Machine Learning is NOT magic. — Shift of Thoughts During the early stages of my experience with Machine Learning, my problem solving philosophy was to focus on modelling. As my entry in Machine Learning started with Deep Learning, complex neural network architectures from the state-of-the-art research papers showed exceptional results. …