brighter AIinGenerate visionThe #paperoftheweek is “RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes”Multi-domain image-to-image translation methods usually take an image and some target attributes as inputs and generate an output image…Apr 30, 2020Apr 30, 2020
brighter AIinGenerate visionThe #paperoftheweek is “High-Resolution Daytime Translation Without Domain Labels”Authors develop the High-Resolution Daytime Translation (HiDT) model that can learn to realistically change the appearance of input image…Apr 9, 2020Apr 9, 2020
brighter AIinGenerate visionThe #paperoftheweek is “StyleGAN2 Distillation for Feed-forward Image Manipulation”There are two types of neural network architecture that allow efficient image manipulation: neural networks trained on either paired or…Mar 30, 2020Mar 30, 2020
brighter AIinGenerate visionSelf-Supervised Linear Motion DeblurringHaving labeled data to train ML/DL models is an expensive resource. Recently the development of self-supervised algorithms has gained…Mar 5, 2020Mar 5, 2020
brighter AIinGenerate visionThe #paperoftheweek is “Deep Predictive Coding Networks for Video Prediction and Unsupervised…One of the common issues when working on video data for tasks like object recognition, tracking, or segmentation is the high cost of…Feb 14, 2020Feb 14, 2020
brighter AIinGenerate visionThe #paperoftheweek is “AUGMIX: A Simple Data Processing Method to Improve Robustness and…Modern deep neural networks can achieve high accuracy when the training distribution and test distribution are identically distributed…Feb 3, 2020Feb 3, 2020
brighter AIinGenerate visionThe #paperoftheweek is “A critique of pure learning and what artificial neural networks can learn…The current success of artificial neural networks (ANNs) has shaken society up, not only by the tasks it can already solve but for the…Sep 26, 2019Sep 26, 2019
brighter AIinGenerate visionThe #paperoftheweek is “Diversity-Sensitive Conditional Generative Adversarial Networks”In Conditional GANs, the generator is not only fed with a randomly sampled latent but also with extra information. This extra information…Jul 19, 2019Jul 19, 2019
brighter AIinGenerate visionThe #paperoftheweek is “The Lottery thicket Hypothesis: Finding Sparse, Trainable Neural Networks”.The authors of this paper propose a novel way to prune large trained neural networks, generating sparse and lightweight subnetworks…May 31, 2019May 31, 2019
brighter AIinGenerate vision3 Trends for the Future of Data PrivacyOne Year of GDPR from the Perspective of a Privacy Tech StartupMay 28, 2019May 28, 2019
