Image recognition with DL AlexNet VGG Inception ResNet VisionTransformer VIT and Scaling
#############################
Video Source: www.youtube.com/watch?v=WPN1932Cwh8
This video introduces how to read papers by quickly skimming through the main ideas of some of the most important papers in the field of image recognition and deep learning in general in the last decade: AlexNet, VGG, Inception, ResNet, EfficientNet, and VisionTransformer (ViT). Finally, it ends up with some comments on trends that we observe in the last decade, in particular the bitter lesson on scaling (http://www.incompleteideas.net/IncIde...) and how can we make use of new paradigms such as parameter-efficient transfer learning to take advantage of these trends. • Complementary to this video there's this other presentation I made on one particular topic that is my focus: fine-grained image recognition . If you're interested I link the presentation below: • https://drive.google.com/file/d/1QY-G...
#############################