All bites
The whole library, newest first. Filter by what you are here for, or pick a topic if you already know.
4330 bites
Page 88
Point cloud vs voxel grid vs NeRF
Point clouds are sparse and fast but unstructured, voxels are regular for collision checks but memory-heavy, NeRFs render photorealistically but are slow.
Zero-shot classification with CLIP
Encode image and label prompts into a shared space, compare via cosine similarity, pick the highest.
Contrastive learning vs masked image modeling
Contrastive aligns augmented views via instance discrimination; MAE reconstructs masked patches; they differ in augmentation and fine-tuning.
When a homography is a valid model
Homography holds for pure rotation or a planar scene; it fails with translation plus 3D parallax, where epipolar geometry applies.
Challenges deploying a model on edge hardware
Limited memory and compute cause latency, thermal and power limits, accuracy loss from compression, operator support gaps.
Designing a multi-object tracker
Detect per frame, predict motion with a filter, associate via IoU and appearance, manage track lifecycle, handle occlusion with re-ID.
One-stage vs two-stage detectors
One-stage predicts boxes directly for speed; two-stage proposes then refines for accuracy; focal loss narrows the gap.
Non-maximum suppression in detection
Detectors emit many overlapping boxes per object; NMS keeps the highest-scoring box and removes others above an IoU threshold.
Single vs multi-image super-resolution
SISR hallucinates detail from one image, multi-image fuses sub-pixel shifts; pixel losses blur, perceptual or GAN losses add realism.
Triangulating 3D points from two views
Back-project each 2D point into a ray, intersect rays from both cameras using known poses, solve via DLT and refine by minimizing reprojection error.
The role of anchor boxes in detectors
Anchors are reference boxes of set scales and ratios; the model regresses offsets, framing detection as classification plus refinement; downsides are tuning, imbalance.
Why averaging shots reduces image noise
Random noise averages out while signal stays, so SNR rises with the square root of frame count; limits include motion and fixed-pattern noise.
PTQ versus QAT for model quantization
PTQ quantizes a trained model with calibration data, fast but may lose accuracy; QAT simulates quantization in training so weights adapt.
Homography vs fundamental matrix degeneracy
Homography fits planar scenes or pure rotation; fitting a fundamental matrix there is degenerate because points lack depth variation.
How is IoU computed and why prefer mIoU?
IoU is intersection over union of predicted and true pixels; mIoU averages per class; pixel accuracy is dominated by background.
Loss functions for imbalanced medical segmentation
Cross-entropy is swamped by background; Dice optimizes overlap directly; Focal down-weights easy pixels.
Design real-time multi-object tracking for AV
Fast detector, Kalman motion model, Hungarian association on IoU plus appearance, track lifecycle for occlusions.
Filter-based vs optimization-based SLAM
EKF folds past poses into one Gaussian; optimization keeps a sparse graph and re-linearizes; the latter wins on accuracy and loop closure.
What does N-way K-shot classification mean?
N is classes per episode, K is labeled examples per class in the support set, prediction is on a separate query set.
Design an active learning loop for detection
Seed-train, score the pool by uncertainty plus diversity, batch to annotators, retrain, repeat.