COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > CuAI (Cambridge University Artificial Intelligence Society) > Better, faster, stronger: Ten years of computer vision and deep learning | Google
Better, faster, stronger: Ten years of computer vision and deep learning | GoogleAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact srj38. The field of computer vision was revolutionized in 2012 with the advent of deep learning. We’re in the year 2021 and the latest results look poised to shake up the field again : Non-convolutional architectures produce state of the art results, and they leverage of large amounts of weakly labelled data leads to impressive results on data never seen during training. This talk will start from the very basics using ML for image classification, dive into transfer learning, and finally focus on recent research results, such as vision transformers and contrastive learning from text and images. This talk is part of the CuAI (Cambridge University Artificial Intelligence Society) series. This talk is included in these lists:Note that ex-directory lists are not shown. |
Other listsMott Colloquium Computer Modelling in Biology Spring School 2009 - "Regeneration and Plasticity of Neural Circuits"Other talksA data-driven approach to advancing cognitive neuroscience TMS Week 4 - Prof. Piers Coleman of Rutgers University - Atoms, Particles and Fractionalization Neural ODE Processes Feeding and feedback from little monsters: black holes in dwarf galaxies Linaro/96 Boards: Innovation in Autonomous Driving powered by Open Source Heterogeneous Computing Platform A New Method of Determining Black Hole Spin and Accretion Disk Properties for Supermassive and Stellar-mass Black Holes |