Contrastive Learning of visual representations - SimCLR (paper illustrated)
SimCLR Contrastive Learning of visual representations: A Simple Framework for Contrastive Learning of Visual Representations
SimCLR presents a series of findings which work in harmony to produce the results no other self-supervised learning method has been able to. It uses a simple ResNet-50 architecture and still beats the state-of-the-art result. This video explains the ideas and results from the SimCLR paper.
Paper link: https://arxiv.org/abs/2002.05709
Google Blog: https://ai.googleblog.com/2020/04/adv...
Official code: https://github.com/google-research/si...
YouTube: / aibites
Twitter: / ai_bites
📚 📚 📚 BOOKS I HAVE READ, REFER AND RECOMMEND 📚 📚 📚
📖 Deep Learning by Ian Goodfellow - https://amzn.to/3Wnyixv
📙 Pattern Recognition and Machine Learning by Christopher M. Bishop - https://amzn.to/3ZVnQQA
📗 Machine Learning: A Probabilistic Perspective by Kevin Murphy - https://amzn.to/3kAqThb
📘 Multiple View Geometry in Computer Vision by R Hartley and A Zisserman - https://amzn.to/3XKVOWi
#ai #research #machinelearning