48 articles on computer vision — convolutional networks, object detection, image segmentation, and transfer learning.
Part of the xbe.at knowledge base. ← Back to index
- Convolution operations: kernels, padding, stride, pooling
- MaxPooling, average pooling, global pooling
- Batch normalization in CNNs, dropout for regularization
- Preventing overfitting in convolutional networks
- Classic nets: VGG, AlexNet, ZFNet, Inception, ResNet
- Vision Transformer (ViT)
- Implementing and comparing architectures on CIFAR-10, ImageNet
- Fine-tuning pre-trained models (VGG, ResNet, and others)
- 7 transfer learning models for CNNs
- Domain adaptation for computer vision
- YOLO object detection with Python
- Image segmentation with K-Means, SAM, MASA
- Deep Dive into SAM (Segment Anything Model)
- Hidden flaws in object detection models
- Grad-CAM: visualizing CNN decision-making
- Visualizing batch normalization's impact on CNN evolution
- Intuition behind convolution and pooling
- 3D graphics fundamentals, monocular depth estimation
- Face recognition, face generation (Active Shape Model)
- ECG analysis with CNNs and transfer learning
- Mastering YOLO Object Detection with Python
- Visualizing CNN Decision-Making with Grad-CAM
- Deep Dive into Image Segmentation with SAM
- Deep Residual Learning for Image Recognition in Python
- ImageNet Classification with Deep Convolutional Neural Networks