A25 - Computer Vision by Learning
|Year||May 9-13, 2022|
|Registration||Registration period closed|
|Update March 18, 2022. The provisional program is now available! Please see:
Computer Vision by Learning featuring an invited tutorial by Serge Belongie
This graduate course is especially meant for Ph.D. students who have basic familiarity with computer vision, image processing, and machine learning and want to upsurge their knowledge and machinery to the state-of-the-art, with direct utility in their own research. The topic of attention is the challenge of computer vision by learning. We address the theoretical foundations of computer vision in conjunction with machine learning and present algorithms that achieve state-of-the-art performance while maintaining efficient execution with minimal supervision. This year we explain and emphasize on computer vision by deep learning, including challenges like image classification by data-efficient convolutional neural networks, face generation by Generative Adversarial Networks, action recognition with point-supervision, and explainability by vision and language embeddings.
Note that the number of seats for this course is limited.
|We give an overview of the latest developments and future trends in the field on the basis of several recent challenges, and we indicate how to obtain improvements in the near future.|
|For the lab, you are expected to bring your own device, either a laptop with a good GPU or a laptop that can connect to a workstation with a good GPU. In case you cannot connect to a GPU, you should make a CoLAB Google Account and make sure you can run a GPU powered notebook (You can turn the GPU on by the following steps: Edit->Notebook settings->Hardware accelerator->GPU)|