More in AI & ML — page 14
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.