PinnedOlga MindlinaMy experiments with zero-shot detection.Recently I’ve become interested in zero-shot learning. I tried CLIP — studied the concept of image vs text similarity and image…Nov 3, 2023Nov 3, 2023
Olga MindlinaDepth Estimation: problem, use cases, solutions and practical experiments using EDEN — Multimodal…1.What is depth in computer vision and why we need itAug 211Aug 211
Olga MindlinainPython’s GurusClassification of medical images: Should you build a model from scratch or use transfer learning…The focus of this article is the methodology of training models on custom datasets. I’ve already discussed two solutions for the problem of…Jun 15Jun 15
Olga MindlinaNaive art plus Generative AI (VQGAN + CLIP). Practical experimentsThis post focuses on applying generative models to various art styles rather than delving deeply into the details of generative models…May 14May 14
Olga MindlinaGaze Estimation: problem, solutions and practical experiments.Gaze estimation is an important problem in computer vision with various applications in real life, including health care, human–computer…May 5May 5
Olga MindlinaVision Transformer for semantic segmentation on medical images. Practical uses and experiments.The focus of this article is Vision Transformer (ViT) and its practical applications for semantic segmentation problem. I discuss again the…Mar 91Mar 91
Olga MindlinaSegmentation of abnormality areas on medical images. Practical uses of U-Net and experiments.Semantic segmentation is one of important problems in Computer Vision. Semantic segmentation is used to identify pixel groups associated…Feb 23Feb 23
Olga MindlinaVision Transformer for classification on medical images. Practical uses and experiments.The focus of this article is Vision Transformer (ViT) and its practical applications for real life problems. I discuss again the task of…Jan 74Jan 74
Olga MindlinaVQGAN. From image reconstruction to new image generation step by step.The object of this article is VQGAN as a whole system for new image generation. I’ve already started the discussion of the part of VQGAN —…Dec 15, 2023Dec 15, 2023
Olga MindlinaAutoencoders. Practical use for image denoising, image recovering and new image generationAutoencoders are type of a deep learning algorithm that performs encoding of an input to a compressed representation and decoding of the…Nov 28, 2023Nov 28, 2023