NF-Nets: Normalizer Free Nets

The beginning of the downfall for Batch Normalization? Introduction DeepMind released a new family of state-of-the-art networks for Image Classification that has surpassed the previous best - EfficientNet - by quite a margin. The main idea behind the new architecture is the use of Normalizer Free Neural Nets or NF-Nets to train networks instead of … Continue reading NF-Nets: Normalizer Free Nets

Interactive Video Stylization Using Few-Shot Patch-Based Training

Style transfer is an interesting problem in machine learning research where we have two input images, one for content and another for style, and the output is our content image re-imagined with this new style. The content can be a photo straight from our camera, and the style can be a painting, which leads to … Continue reading Interactive Video Stylization Using Few-Shot Patch-Based Training