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 58

Computer Vision1 min read

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.

Computer Vision2 min read

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.

Computer Vision1 min read

Challenges deploying a model on edge hardware

Limited memory and compute cause latency, thermal and power limits, accuracy loss from compression, operator support gaps.

Computer Vision2 min read

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.

Computer Vision2 min read

Contrastive learning vs masked image modeling

Contrastive aligns augmented views via instance discrimination; MAE reconstructs masked patches; they differ in augmentation and fine-tuning.

Computer Vision2 min read

Zero-shot classification with CLIP

Encode image and label prompts into a shared space, compare via cosine similarity, pick the highest.

Computer Vision2 min read

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.

Computer Vision1 min read

Cross-attention in transformer VQA models

Text queries attend over image regions, learning alignment that grounds words to visual content.

Computer Vision1 min read

The data association problem in SLAM

Matching observations to landmarks, why wrong matches corrupt the map, robust techniques like RANSAC and descriptor matching.

Computer Vision1 min read

Core components of visual SLAM

Tracking estimates per-frame pose, mapping builds and refines the 3D map, loop closure detects revisits and corrects drift.

Computer Vision1 min read

Adapting a 2D CNN for video action recognition

Run the 2D CNN per frame, pool features over time, optionally add two-stream or 3D conv.

Computer Vision1 min read

Deploying segmentation on edge devices

Pick efficient architectures, apply INT8 quantization, distill from a large teacher.

Computer Vision1 min read

Improving small object detection

Raise input resolution and tile, use feature pyramids for high-res features, tune anchors and copy-paste augmentation.

Computer Vision1 min read

What is Bundle Adjustment and why is it tractable?

Jointly refine 3D points and camera poses by minimizing reprojection error, expensive due to many coupled parameters; sparsity of the Jacobian and the Schur complement make it tractable.

Computer Vision1 min read

Why learn detection and description jointly like SuperPoint?

A shared backbone jointly optimizes detection and description for matching, sharing computation and learning data-driven robustness instead of hand-crafted heuristics.

Computer Vision1 min read

Feature detector vs feature descriptor.

A detector finds where interesting points are, a descriptor encodes the local appearance around each so points can be matched.

Computer Vision1 min read

How is an HDR radiance map constructed from exposures?

Recover the inverse camera response function from corresponding pixels, linearize each exposure to radiance, then merge with confidence weights into a floating-point radiance map.

Computer Vision1 min read

Design drift detection and retraining for a CV model.

Monitor input and prediction distributions plus delayed labels, detect data and concept drift, trigger an automated retrain-validate-deploy pipeline with versioning and rollback.

Computer Vision1 min read

Design a cashierless retail checkout vision system.

Multi-camera coverage, person tracking and re-ID, product detection plus action recognition for take or return, sensor fusion, edge-cloud split, and failure handling.

Computer Vision1 min read

CPU vs GPU vs Edge TPU for inference.

CPU is flexible but slow, GPU offers massive parallelism at high power, Edge TPU gives efficient low-power int8 inference but is constrained; choose by latency, power, cost, and model fit.