Sik-Ho TsangReview — DETR: End-to-End Object Detection with TransformersAnchor Free Object Detection Using ResNet+TransformerApr 24, 2022501Apr 24, 2022501
Sik-Ho TsangBrief Review — VinVL: Revisiting Visual Representations in Vision-Language ModelsVinVL, Improving Visual Features by Better Models, Datasets & PretrainingDec 10, 20224Dec 10, 20224
InSyncedReviewbySyncedNeurIPS 2022 | Meta AI, Stanford & Tübingen U Beat Neural Scaling Laws via Data PruningStudies on various machine learning models have shown that applying neural scaling laws — increasing compute, model size, and pretraining…Nov 29, 202271Nov 29, 202271
InTowards AIbyMustafa GültekinOverview Of Vision Transformers Is All You NeedHow are Transformers the next breakthrough in computer vision?Sep 10, 20221611Sep 10, 20221611
InV7 LabsbyV7 Editorial TeamThe Essential Guide to Pytorch Loss FunctionsLet’s take a deep dive into the loss functions and their implementation in the PyTorch framework.Oct 7, 2022264Oct 7, 2022264
GayathriL1 & L2 NORMSIn my last post, I covered the introduction to Regularization in supervised learning models. In this post, let’s go over some of the…Nov 3, 202259Nov 3, 202259
InSceneBoxbyYaser KhalighiBringing Synthetic Data into Computer Vision Training PipelinesTL;DR: Synthetic data is helping fuel the future of computer vision ML and should be first-class citizens in any data management solution…Aug 2, 2022103Aug 2, 2022103