PinnedIgor SusmeljinTowards Data ScienceData Curation Guide for Computer VisionData curation in computer vision lacks standardization, leaving many practitioners unsure how to do it correctly. We summarized some of the…Mar 9, 2023Mar 9, 2023
PinnedIgor SusmeljA Guide for Active Learning in Computer VisionLearn how active learning can be used to build a data flywheel where only data is getting labeled and used for training that actually…Feb 3, 2023Feb 3, 2023
PinnedIgor SusmeljSelf-Supervised Models are More Robust and FairA recent paper from Meta AI Research shows that their new 10 billion parameter model trained using self-supervised learning breaks new…Apr 6, 2022Apr 6, 2022
Igor SusmeljinTowards AIApple M1 and M2 Performance for Training SSL ModelsWe want to know how fast Apple M1 and M2 chips are for training self-supervised learning models.Oct 14, 2023Oct 14, 2023
Igor SusmeljActive Learning Strategies Compared for YOLOv8 on LincolnbeetLearn how different data selection strategies impact model accuracy. We use the lincolnbeet dataset and YOLOv8 model for our experiments.Apr 24, 2023Apr 24, 2023
Igor SusmeljinLightlyLightly’s Data Curation ApproachThis overview is intended to help everyone understand how Lightly works behind the scenes and how it can be used for your data curation…Mar 15, 2022Mar 15, 2022
Igor SusmeljinTowards Data ScienceTrain Test Split in Deep LearningOne of the golden rules in machine learning is to split your dataset into train, validation, and test set. Learn how to bypass the most…Feb 23, 2022Feb 23, 2022
Igor SusmeljinTowards AIEmbedded COVID mask detection on an Arm Cortex-M7 processor using PyTorchHow we built a visual COVID-19 mask quality inspection prototype running on-device on an OpenMV-H7 board and the challenges on the way.Feb 6, 20211Feb 6, 20211
Igor SusmeljinDataDrivenInvestorThe Advantage of Self-Supervised LearningA few personal thoughts on why self-supervised learning will have a strong impact on AI. From recent NLP to computer vision papers.Jan 28, 2021Jan 28, 2021