Overview
Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Discover advanced techniques for large-scale image classification in this 54-minute video from the Nvidia Grandmaster Series. Learn how Kaggle Grandmasters of NVIDIA (KGMON) built winning models for the Google Landmark Recognition 2020 competition, tackling the challenge of recognizing landmarks across 81,000+ classes. Explore classical approaches, winning solutions, validation strategies, code efficiency, and modeling techniques. Gain insights into third-place solutions, including architecture, fine-tuning, postprocessing, and ensemble methods. Delve into competition-specific strategies like cutout augmentation and label submitting. Led by industry experts, this comprehensive tutorial covers everything from introductory concepts to advanced topics like vaccine degradation, providing valuable knowledge for data scientists and AI enthusiasts interested in computer vision and large-scale image classification challenges.
Syllabus
Introduction
Welcome
Competition
Classical Approach
Winning Solution
Validation Strategy
Code Efficiency
Modeling
Third Place Solution
Architecture
Finetuning
Postprocessing
Ensemble
Competitions
Cutout Augmentation
Label Submitting
Vaccine Degradation
Taught by
NVIDIA Developer
Tags
Reviews
4.9 rating, based on 9 Class Central reviews
Showing Class Central Sort
-
This course provides a clear and practical overview of large-scale image classification using modern deep learning techniques. The explanations are concise, well-structured, and easy to follow, even for learners new to the topic.
Overall, it is a valuable resource for understanding how NVIDIA technologies and GPUs are applied in real-world computer vision tasks, especially at scale. -
Taking the course "How to Perform Large-Scale Image Classification" was a valuable experience that helped me grow from a beginner into a more confident practitioner in deep learning. I gained practical skills in handling large image datasets, understood the workings of CNNs, and learned the benefits of transfer learning. Most importantly, I became familiar with training models at scale using GPUs and cloud strategies. This course gave me both the knowledge and confidence to take on real-world computer vision projects.
-
Amazing content on image processing in AI solutions! The techniques and functions presented by the last group are not only interesting, but also highly useful for a wide range of creative projects.
-
This course on "How to Perform Large-Scale Image Classification" by Nvidia was incredibly insightful and well-structured. It provides a solid introduction to key concepts in image classification, including model training, data preparation, and the use of pre-trained neural networks. The instructors explain the material clearly, and the visual demonstrations greatly enhance understanding. I particularly appreciated the practical examples and the use of real-world datasets. This course is highly recommended for anyone interested in deep learning or computer vision
-
I recently completed the Large-Scale Image Classification course by Nvidia, hosted on Class Central, and I found it to be an incredibly insightful resource for understanding advanced techniques in image recognition. The course focuses on the 1st, 3rd, and 7th place solutions from Google’s Landmark Recognition Challenge 2020 on Kaggle, which made it highly practical and relevant to real-world problems.
-
Buena Charla y muy bien guiada, lastima que no hubo ejemplos practicos con los cuales nos permita practicas sobre lo hablado
-
Hi, this is my first time being watching an episode in the Grandmater series. I really enjoyed learning different approaches of dealing with such large-scale image classification tasks. This really interested me, I'll surely be joining for the further similar episodes.
Thank you -
Very useful information and clear on topics thanks to person who made it clear
This course will be useful for me at future -
Poderia ter uma demonstração como faz a classificação de larga escala, não só falar dos fundamentos como é como eles usam