🤖 AI &amp; ML

U-Net architecture and its skip connections

U-Net has a contracting encoder, an expanding decoder, and skip connections that concatenate matching-resolution encoder features into the decoder to recover spatial detail lost in downsampling.

Semantic versus instance segmentation

Semantic segmentation labels each pixel by class but merges objects of the same class; instance segmentation also separates individual objects.

Detector head losses: regression versus classification

The head splits into a classification branch using cross-entropy over classes and a regression branch using a robust Smooth L1 or IoU loss on box offsets, combined as a weighted sum.

Deploying real-time detection on edge devices

Pick an efficient one-stage detector, train with augmentation, then quantize, prune, and compile to a hardware-accelerated runtime, measuring latency and accuracy tradeoffs.

Focal Loss and class imbalance in detectors

Focal loss multiplies cross-entropy by a (1-p)^gamma factor that down-weights easy, well-classified examples so the vast easy background does not swamp the loss.

easy2 min read

Mean Average Precision in object detection

AP is the area under the precision-recall curve per class; mAP averages AP over classes, and COCO also averages over IoU thresholds.

Intersection over Union for detection

IoU is the area of overlap divided by the area of union of predicted and ground-truth boxes; a threshold decides true positives.

Image classification versus object detection

Classification assigns one label to the whole image; detection localizes and labels multiple objects with bounding boxes and class scores.

advanced1 min read

Translation equivariance versus invariance in CNNs

Convolution is equivariant, shifting input shifts feature maps; invariance comes only from pooling and global aggregation. Strict invariance is partial and broken by strided sampling.

Depthwise separable convolution cost savings

Separable conv splits standard conv into per-channel spatial filtering plus a 1x1 pointwise mix, cutting cost by roughly 1/N plus 1/k².

advanced1 min read

Adapting a classification CNN for segmentation

Replace the dense head with conv layers, upsample via transposed convolutions, and fuse encoder skip connections to recover spatial detail lost to downsampling.

Uses of the 1x1 convolution

A 1x1 conv is a per-pixel linear combination across channels; it reshapes channel depth cheaply and adds nonlinearity. Uses: dimensionality reduction in bottlenecks and channel mixing.

Receptive fields in convolutional networks

Receptive field is the input region affecting a neuron; it grows with depth, larger kernels, and stride. It matters for capturing context in detection and segmentation.

ResNet residual blocks and the degradation problem

A residual block learns F(x) and adds the identity input x, so layers fit a residual; this eases gradient flow and solves the degradation problem.

Regularization techniques for an overfitting CNN

Data augmentation expands the effective dataset, dropout prevents co-adaptation, weight decay penalizes large weights, plus early stopping and batchnorm.

Why CNNs need nonlinear activations like ReLU

ReLU introduces nonlinearity letting stacked layers model complex functions; without it any stack collapses to a single linear map.

Max pooling versus strided convolution

Pooling downsamples and adds small translation invariance with no parameters; strided conv learns its downsampling but adds parameters.

How a convolutional layer works

Learnable kernels slide over the input computing dot products, with stride controlling step size and padding controlling output size.

advanced1 min read

Stereo rectification math and its artifacts

Rectification warps both images by homographies so epipolar lines become horizontal and aligned.