YoVDO

Learning to Classify Images Without Labels - Paper Explained

Offered By: Yannic Kilcher via YouTube

Tags

Unsupervised Learning Courses Computer Vision Courses Image Classification Courses Clustering Courses Representation Learning Courses

Course Description

Overview

Explore a comprehensive video explanation of a research paper that investigates a novel approach to image classification without labels. Delve into the combination of representation learning, clustering, and self-labeling techniques used to group visually similar images together. Learn about the problem statement, limitations of naive clustering, representation learning methods, nearest-neighbor-based clustering, and self-labeling processes. Examine the experimental results, including impressive performance on benchmark datasets like CIFAR10, CIFAR100-20, and STL10. Discover how this approach scales to ImageNet with 200 randomly selected classes and even all 1000 classes. Gain insights into the two-step approach that decouples feature learning and clustering, leading to significant improvements over state-of-the-art methods in unsupervised image classification.

Syllabus

- Intro & High-level Overview
- Problem Statement
- Why naive Clustering does not work
- Representation Learning
- Nearest-neighbor-based Clustering
- Self-Labeling
- Experiments
- ImageNet Experiments
- Overclustering


Taught by

Yannic Kilcher

Related Courses

Machine Learning: Unsupervised Learning
Brown University via Udacity
Practical Predictive Analytics: Models and Methods
University of Washington via Coursera
Поиск структуры в данных
Moscow Institute of Physics and Technology via Coursera
Statistical Machine Learning
Carnegie Mellon University via Independent
FA17: Machine Learning
Georgia Institute of Technology via edX