Vatsal SaglaniQuestion Classification using Self-Attention Transformer — Part 1.1Understanding the Multi-Head Self-Attention Transformer network with code in PyTorchJan 1, 2021Jan 1, 2021
Vatsal SaglaniWhat is CLIP (Contrastive Language — Image Pre-training) and how it can be used for semantic image…Deep Learning way to search imagesFeb 9, 2021Feb 9, 2021
Vatsal SaglaniPaper Explained: TransGAN — Two Transformers can make One Strong GANA CNN free GAN networkFeb 26, 20211Feb 26, 20211
Vatsal SaglaniHow Can Self-Supervised Models Benefit Different Computer Vision Tasks?SimCLRv2 explainedMar 27, 2021Mar 27, 2021