InLevel Up CodingbyKasrasadatsharifi·Nov 6Vision Transformers Part1: Why Replace Convolution with AttentionUnderstanding vision transformers foundation, architectural differences and performance comparisons with CNNs. Some of the graphs in this…A response icon1A response icon1
InTowards AIbyKasrasadatsharifi·Oct 28ConvNeXt Explained: How CNNs Borrowed From Vision TransformersUnderstanding the architectural decisions behind ConvNeXt, advantages and disadvantages over Vision Transformers and older CNNs.A response icon2A response icon2
InTowards AIbyKasrasadatsharifi·Oct 20When Does a VLM Add Value to Your Project?This is a personal project that I worked on to understand the advantages and disadvantages of VLMs in computer vision projects. Figures…
InLevel Up CodingbyKasrasadatsharifi·Oct 16How much should you fine-tune your vision transformer with limited dataIn this experiment I wanted to understand how much of my Vision Transformer (ViT) should I fine tune to my limited dataset for a better…A response icon2A response icon2
InLevel Up CodingbyKasrasadatsharifi·Oct 7From OpenCV experiments to an Interactive Image ProcessorThis was a personal experiment to understand and implement some of the traditional image processing techniques.
InLevel Up CodingbyKasrasadatsharifi·Aug 18, 2025Residual Network Experimentation on CIFAR10Residual networks, introduced in Deep Residual Learning for Image Recognition (He et al., 2015; CVPR 2016), are among the most widely used…