tezvyn:

🤖AI & ML

Artificial intelligence, machine learning, and data science

1166 bites

More in AI & ML — page 14

Computer Vision80 sec read

Semantic versus instance segmentation

WHAT IT TESTS: distinguishing two pixel-labeling tasks. OUTLINE: semantic segmentation labels each pixel by class but merges objects of the same class; instance segmentation also separates individual objects.

Computer Vision2 min read

Detector head losses: regression versus classification

WHAT IT TESTS: multi-task loss design in detection heads. OUTLINE: 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.

Computer Vision2 min read

Deploying real-time detection on edge devices

WHAT IT TESTS: end-to-end edge deployment reasoning. OUTLINE: pick an efficient one-stage detector, train with augmentation, then quantize, prune, and compile to a hardware-accelerated runtime, measuring latency and accuracy tradeoffs.

Computer Vision2 min read

Focal Loss and class imbalance in detectors

WHAT IT TESTS: handling extreme class imbalance. OUTLINE: 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.

Computer Vision2 min read

Mean Average Precision in object detection

WHAT IT TESTS: the headline detection metric. OUTLINE: AP is the area under the precision-recall curve per class; mAP averages AP over classes, and COCO also averages over IoU thresholds. RED FLAG: confusing mAP with plain accuracy or ignoring the PR curve.

Computer Vision86 sec read

Intersection over Union for detection

WHAT IT TESTS: the core overlap metric. OUTLINE: IoU is the area of overlap divided by the area of union of predicted and ground-truth boxes; a threshold decides true positives.

Computer Vision79 sec read

Image classification versus object detection

WHAT IT TESTS: basic task definitions. OUTLINE: classification assigns one label to the whole image; detection localizes and labels multiple objects with bounding boxes and class scores.

Computer Vision88 sec read

Translation equivariance versus invariance in CNNs

WHAT IT TESTS: precise reasoning about CNN symmetries. OUTLINE: 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.

Computer Vision2 min read

Depthwise separable convolution cost savings

WHAT IT TESTS: efficient convolution factorization. OUTLINE: separable conv splits standard conv into per-channel spatial filtering plus a 1x1 pointwise mix, cutting cost by roughly 1/N plus 1/k².

Computer Vision89 sec read

Adapting a classification CNN for segmentation

WHAT IT TESTS: turning a classifier into a dense predictor. OUTLINE: replace the dense head with conv layers, upsample via transposed convolutions, and fuse encoder skip connections to recover spatial detail lost to downsampling.

Computer Vision2 min read

Uses of the 1x1 convolution

WHAT IT TESTS: channel-wise operations and efficient design. OUTLINE: 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.

Computer Vision89 sec read

Receptive fields in convolutional networks

WHAT IT TESTS: how spatial context accumulates in CNNs. OUTLINE: 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.

Computer Vision85 sec read

ResNet residual blocks and the degradation problem

WHAT IT TESTS: why skip connections enable very deep nets. OUTLINE: 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.

Computer Vision80 sec read

Regularization techniques for an overfitting CNN

WHAT IT TESTS: practical remedies for overfitting and their mechanisms. OUTLINE: data augmentation expands the effective dataset, dropout prevents co-adaptation, weight decay penalizes large weights, plus early stopping and batchnorm.

Computer Vision83 sec read

Why CNNs need nonlinear activations like ReLU

WHAT IT TESTS: why nonlinearity matters in deep networks. OUTLINE: ReLU introduces nonlinearity letting stacked layers model complex functions; without it any stack collapses to a single linear map.

Computer Vision80 sec read

Max pooling versus strided convolution

WHAT IT TESTS: downsampling tradeoffs in CNNs. OUTLINE: pooling downsamples and adds small translation invariance with no parameters; strided conv learns its downsampling but adds parameters.

Computer Vision85 sec read

How a convolutional layer works

WHAT IT TESTS: the mechanics of convolution. OUTLINE: learnable kernels slide over the input computing dot products, with stride controlling step size and padding controlling output size.

Computer Vision76 sec read

Stereo rectification math and its artifacts

WHAT IT TESTS: epipolar geometry and stereo correspondence. OUTLINE: rectification warps both images by homographies so epipolar lines become horizontal and aligned.

Computer Vision85 sec read

The PnP problem in Structure from Motion

WHAT IT TESTS: geometric camera pose estimation. OUTLINE: PnP recovers a camera's pose from known 3D points and their 2D projections; it registers new frames against the existing point cloud in SfM. RED FLAG: confusing it with triangulation.

Computer Vision2 min read

Incremental Structure from Motion pipeline

WHAT IT TESTS: 3D reconstruction workflow. OUTLINE: detect and match features, estimate two-view geometry, triangulate, then incrementally add images with PnP and refine via bundle adjustment.