Image Processing
Linear filtering and convolution, blur filters, image derivatives, filtering in space and time, sampling without aliasing, and statistical image priors.
CNNs
Convolutional neural networks for image classification, including layer types, architectures, and visualization techniques.
Object Detection
Detecting and localizing objects in images using two-stage and single-stage deep learning detectors.
Object Segmentation
Pixel-wise classification for semantic and instance segmentation using Mask RCNN and UNet.
Image processing
Classical image processing treats an image as a signal. Filtering, differentiation, and sampling are the operations that CNNs later learn and stack.Convolution and Linear Filters
Linear translation-invariant systems, convolution, boundary handling, and template matching.
Smoothing an Image with Blur Filters
Box, Gaussian, and binomial filters and their frequency responses.
Measuring Change with Image Derivatives
Discrete and Gaussian derivatives, the Laplacian, sharpening, and Retinex.
Filtering in Space and Time
A video as a space-time volume, velocity-tuned blur, and velocity-nulling filters.
Sampling an Image Without Aliasing
The sampling theorem, reconstruction, sampling lattices, and anti-aliasing.
Image priors
What natural images have in common, and how that knowledge becomes a prior for denoising, synthesis, and inference.What Natural Images Have in Common
The 1/f power law, heavy-tailed derivatives, and denoising with image priors.
Synthesizing Textures
Texture synthesis by histogram matching and by copying neighborhoods.
Markov Random Fields and Belief Propagation
Markov random fields and belief propagation for denoising, segmentation, and stereo.
Convolutional neural networks
CNNs are the backbone of modern computer vision systems, enabling image classification, feature extraction, and visual understanding.CNN introduction
Introduction to convolutional neural networks.
CNN layers
Understanding CNN layer types and operations.
CNN architectures
Example architectures: LeNet, AlexNet, VGG, ResNet.
Feature extraction: ResNet
ResNet as a backbone for downstream vision tasks.
Object detection
Object detection covers scene understanding fundamentals, evaluation metrics, and the evolution from two-stage (RCNN family) to single-stage (YOLO family) detectors.Scene understanding
Detection vs classification, the detection pipeline, region proposals, FCNs, and the COCO dataset.
Detection metrics
Precision, recall, mAP, and IoU for evaluating detectors.
From R-CNN to Faster R-CNN
Video references that walk through R-CNN, Fast R-CNN, Faster R-CNN and mAP.
RCNN
Region-based CNN: selective search, CNN features, SVM classification.
Fast RCNN
Shared convolutional features and ROI pooling for end-to-end training.
Faster RCNN
Region Proposal Network enabling fully end-to-end two-stage detection.
Faster RCNN from scratch (PyTorch)
A six-notebook series building every Faster RCNN component from scratch in pure PyTorch, from COCO data loading through end-to-end training and inference.01 · COCO dataloader
Streaming COCO from Hugging Face, collation, and anchor target assignment.
02 · Backbone
ResNet50 feature pyramid network (FPN) with lateral connections.
03 · RPN
Region Proposal Network: anchor generation, objectness head, NMS.
04 · ROI head
ROI Align, two-layer MLP head, and sibling classification and regression predictors.
05 · Training
End-to-end training with AMP and gradient checkpointing on COCO streaming data.
06 · Inference
Checkpoint loading, COCO validation inference, proposal and detection visualization.
YOLO from scratch (PyTorch)
A five-notebook series building YOLOv8-style single-stage detection in pure PyTorch, from data loading through inference and evaluation.YOLO introduction
Single-stage detection design philosophy, anchor-free heads, and the YOLO architecture family.
01 · COCO dataloader
Streaming COCO, grid target assignment, and mosaic augmentation.
02 · Backbone
CSPDarknet backbone with C2f bottleneck blocks.
03 · Neck and head
PANet feature pyramid neck and decoupled detection head.
04 · Loss and training
Task-aligned assignment, distribution focal loss, and training loop.
05 · Inference and evaluation
NMS post-processing, COCO mAP evaluation, and latency benchmarks.
Object segmentation
Instance and semantic segmentation extend object detection to produce pixel-level masks, enabling fine-grained scene understanding.Mask RCNN
Extending Faster RCNN with a mask head for instance segmentation.
Mask RCNN · TF demo
Running inference with the TensorFlow Mask RCNN implementation.
Mask RCNN · inspect data
Visualizing COCO data loading, augmentation, and anchor generation.
Mask RCNN · inspect model
Layer-by-layer inspection of model activations and outputs.
Mask RCNN · inspect weights
Visualizing learned filter weights and statistics.
Mask RCNN · PyTorch (Detectron2)
Detectron2 Mask RCNN training and evaluation workflow.
Mask RCNN · torchvision inference
Running pretrained Mask RCNN inference with torchvision.
UNet
Encoder-decoder architecture for semantic segmentation.