xbe.at

Topics

Computer vision

Images in, structure out: convolution, detection, segmentation, transfer learning.

  1. 3D Graphics Foundations Rendering Triangles in Python14 min

    The foundation of 3D graphics begins with understanding coordinate systems. In computer graphics, we represent points in 3D space using vectors containing X...

  2. 3D Packing for Self-Supervised Monocular Depth Estimation13 min

    3D packing is a crucial technique in self-supervised monocular depth estimation, which aims to predict depth from a single image without ground truth depth...

  3. 7 Transfer Learning Models for Convolutional Neural Networks12 min

    Transfer learning is a powerful technique in deep learning where knowledge gained from training on one task is applied to a different but related task. In...

  4. Active Shape Model for Face Image Generation8 min

    Active Shape Models (ASM) are statistical models of shape that can deform to fit new examples. They are particularly useful in face recognition and image...

  5. Advanced ECG Analysis Using Transfer Learning and CNNs7 min

    This project focuses on classifying ECG images using advanced deep learning techniques. We'll explore data preparation, model development, and the...

  6. Best Face Recognition Models in Python10 min

    Face recognition is a biometric technology that identifies or verifies a person's identity using their facial features. This technology has gained...

  7. Comparing 2-Layer CNN Models on CIFAR-108 min

    Two 2-layer CNN models were trained on the CIFAR-10 dataset, resulting in different accuracies. Model A achieved 70% accuracy, while Model B reached 74%....

  8. Convolutional Neural Network Fundamentals13 min

    A convolutional neural network implementation focusing on the fundamental building blocks using NumPy. This base architecture demonstrates the core concepts...

  9. Convolutional Neural Network with Python10 min

    Convolutional operations are fundamental building blocks in neural networks, particularly in computer vision tasks. They enable the network to learn spatial...

  10. Convolutional Neural Networks and Kernels in Python6 min

    Convolutional Neural Networks (CNNs) have revolutionized the field of computer vision and image processing. They are designed to automatically and adaptively...

  11. Convolutional Neural Networks on Manifolds with Python10 min

    Convolutional Neural Networks (CNNs) have revolutionized image processing tasks, but their application to non-Euclidean domains like manifolds presents...

  12. Data Augmentation Techniques for Convolutional Neural Networks12 min

    Data augmentation is a powerful technique used to increase the diversity of training data for convolutional neural networks (CNNs). It involves creating new...

  13. Deep Dive into Image Segmentation with SAM7 min

    The Segment Anything Model (SAM) introduces a novel architecture combining three main components: an image encoder based on Vision Transformers (ViT), a...

  14. Deep Extrinsic Manifold Representation for Computer Vision11 min

    Deep Extrinsic Manifold Representation is a novel approach in computer vision that leverages the power of deep learning to capture and represent complex...

  15. Deep Learning's Impact on Computer Vision10 min

    Computer vision has indeed been greatly impacted by deep learning, but it's important to note that it's not the only success story in the field. While deep...

  16. Deep Residual Learning for Image Recognition in Python8 min

    Deep Residual Learning is a revolutionary approach in image recognition that addresses the problem of vanishing gradients in deep neural networks. It...

  17. Evaluating GANs with Inception Score and FID7 min

    The evaluation of Generative Adversarial Networks requires quantitative metrics to assess the quality and diversity of generated samples. Two fundamental...

  18. Explaining the Purpose of MaxPooling in Convolutional Neural Networks12 min

    MaxPooling is a crucial operation in Convolutional Neural Networks (CNNs) that helps reduce the spatial dimensions of feature maps while retaining the most...

  19. Image Padding and Kernel Stride in Convolutional Neural Networks11 min

    Image padding and kernel stride are crucial concepts in Convolutional Neural Networks (CNNs). They play a significant role in controlling the spatial...

  20. Image Segmentation using K-means Clustering in Python7 min

    Image segmentation is a crucial task in computer vision that involves partitioning an image into multiple segments or regions. K-means clustering is a...

  21. ImageNet Classification with Deep Convolutional Neural Networks in Python10 min

    ImageNet classification is a fundamental task in computer vision that involves categorizing images into predefined classes. Deep Convolutional Neural...

  22. Implementing CNN Image Classification with PyTorch8 min

    Convolutional Neural Networks (CNNs) are a powerful class of deep learning models particularly effective for image classification tasks. PyTorch, a popular...

  23. Introduction to Convolutional Neural Networks in Python10 min

    Convolutional Neural Networks (CNNs) are a class of deep learning models primarily used for processing grid-like data, such as images. They are designed to...

  24. Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry:12 min

    Monocular Direct Sparse Odometry (DSO) is a visual odometry method that estimates camera motion and scene structure from a single camera. It's a key...

  25. Machine Learning Convolutional Neural Network (CNN) and Transfer Learning using Python4 min

    This outline covers the key concepts and techniques related to Convolutional Neural Networks (CNNs) and Transfer Learning using Python. Each slide includes a...

  26. MASA and SAM Image Segmentation Models in Python10 min

    MASA (Matching Anything by Segmenting Anything) and SAM (Segment Anything Model) are advanced computer vision models designed to perform image segmentation...

  27. Mastering Convolutional Neural Networks with Python12 min

    Convolutional Neural Networks are a class of deep learning models designed to process grid-like data, such as images. They're particularly effective for...

  28. Mastering Convolutional Neural Networks! 15 Pro Design Tips10 min

    Before diving into CNN design, it's crucial to clearly identify your objective. Are you working on image classification, object detection, or another...

  29. Mastering YOLO Object Detection with Python12 min

    YOLO (You Only Look Once) is a state-of-the-art, real-time object detection system that revolutionized computer vision. It treats object detection as a...

  30. Object-based Image Classification with Python6 min

    Introduction to Object-based Image Classification