Skip to content
tezvyn:

All bites

The whole library, newest first. Filter by what you are here for, or pick a topic if you already know.

8668 bites

Page 62

Computer Vision1 min read

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.

Computer Vision1 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.

Computer Vision2 min read

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.

Computer Vision1 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.

Computer Vision1 min read

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.

Computer Vision1 min read

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.

Computer Vision1 min read

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.

Computer Vision1 min read

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.

Computer Vision1 min read

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.

Computer Vision1 min read

Max pooling versus strided convolution

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

Computer Vision1 min read

How a convolutional layer works

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

Computer Vision1 min read

Stereo rectification math and its artifacts

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

Computer Vision1 min read

The PnP problem in Structure from Motion

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.

Computer Vision2 min read

Incremental Structure from Motion pipeline

Detect and match features, estimate two-view geometry, triangulate, then incrementally add images with PnP and refine via bundle adjustment.

Computer Vision2 min read

Fundamental matrix versus essential matrix

Both relate corresponding points across two views via the epipolar constraint; the fundamental matrix works in pixel coordinates, the essential matrix in calibrated coordinates and encodes relative pose.

Computer Vision2 min read

Disparity and depth in stereo vision

Disparity is the horizontal shift of a point between left and right images; depth is inversely proportional to disparity given baseline and focal length.

Computer Vision2 min read

Epipolar constraint for correspondence search

The match for p1 must lie on its epipolar line in the second image, reducing a 2D search to 1D; the relation is encoded by the fundamental matrix.

Computer Vision2 min read

Feature choice for real-time mobile SLAM

Pick ORB for fast FAST keypoints and cheap binary descriptors matched by Hamming distance; accept reduced robustness versus SIFT for real-time, low-power operation.

Computer Vision2 min read

CNN features for image retrieval

Pass the image through a pretrained CNN and read activations from a late layer as a descriptor; deeper layers encode semantics, earlier layers encode texture.

Computer Vision2 min read

Bag of Visual Words model

Cluster many local descriptors (e.g. k-means) into visual words; assign each image's features to words; represent the image as a histogram of word counts for a classifier.