Skip to content
tezvyn:

Computer Vision

Image/video models, diffusion, OCR, multimodal

85 bites

Test yourself: Top 30 advanced Computer Vision interview questionsMultiple choice, with the correct answer and why it is correct on every question. Free, no sign-in.

Advanced everything in Computer Vision

advanced1 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.

advanced1 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.

advanced1 min read

How does focus stacking build an all-in-focus image?

Align frames, measure local sharpness as a focus metric, select or blend the sharpest source per region, then composite.

advanced1 min read

Why merge a burst instead of one long low-light exposure?

Short frames avoid motion blur and clipping while averaging cuts noise; align frames and merge robustly, rejecting misaligned regions to avoid ghosting.

advanced1 min read

How does a plenoptic camera enable post-capture refocus?

Light field records ray direction plus position via a microlens array, refocusing shears and integrates the 4D data to choose a virtual focal plane.

advanced1 min read

How do BYOL and Barlow Twins avoid representation collapse?

Collapse is embeddings shrinking to a constant or low-rank subspace; BYOL uses predictor plus momentum target plus stop-gradient, Barlow Twins decorrelates feature dimensions.

advanced1 min read

How does MAML's inner and outer loop work?

Inner loop does task-specific gradient steps from shared init, outer loop updates the init for fast adaptability via second-order gradients.

advanced2 min read

Formulating a multi-step robot manipulation task

Perception detects and localizes the mug, action space spans navigation and manipulation, and a reward shaped over subgoals (reach, grasp, transport, place) with sparse final success guides learning.

advanced2 min read

NeRF limitations and advances for robotics

Original NeRF is slow to train and render, per-scene, static, and needs many calibrated views; address speed with explicit grids or Gaussian splatting, dynamics with time-conditioned fields, and scale with…

advanced2 min read

Designing a high-resolution photorealistic face generator

Weigh StyleGAN's fast, controllable style-based synthesis against diffusion's diversity and stable training; handle scale via progressive or multi-resolution synthesis; protect diversity to avoid mode…

advanced2 min read

DDPM versus DDIM sampling trade-offs

DDPM is a stochastic Markov chain needing many steps; DDIM is a non-Markovian, deterministic sampler that skips steps for far faster inference and reproducible, invertible latents, trading a…

advanced2 min read

Classifier-free guidance in diffusion models

Train one model jointly on conditional and dropped-condition inputs; at inference extrapolate from unconditional toward conditional prediction via a guidance scale, sharpening prompt adherence…

advanced2 min read

Attention in diffusion U-Nets for text conditioning

Self-attention mixes spatial features at low-res blocks; cross-attention has image queries attend to text-token keys/values; placed inside transformer blocks.

advanced2 min read

Pure ViT vs hybrid CNN-Transformer for medical segmentation

Pure ViT captures global context but is data hungry and weak on local detail; hybrid CNN-Transformer gets local features cheaply plus global attention, ideal for scarce…

advanced2 min read

Core principles of a Neural Radiance Field

An MLP maps a 3D point plus view direction to color and density; novel views render by casting rays, sampling points, querying the MLP, and volume-integrating along each ray.

advanced2 min read

Scene flow versus optical flow

Optical flow is 2D pixel motion in the image plane; scene flow is the 3D motion field of points in space, needing depth via stereo, RGB-D, or LiDAR.

advanced2 min read

Self-supervised pretraining for video understanding

Define a label-free task like temporal order prediction or contrastive clip matching that forces temporal reasoning, then fine-tune on labeled action data.

advanced1 min read

Adapting ViT for dense semantic segmentation

Reassemble patch tokens into a 2D feature map, add a decoder, and handle low resolution plus quadratic attention cost.

advanced1 min read

Explain panoptic segmentation and Panoptic Quality

Panoptic assigns every pixel a class and instance id over things and stuff; PQ factors into SQ, average IoU of matches, times RQ, an F1 over matched segments.

advanced2 min read

Detector head losses: regression versus classification

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.

We are hiring for this. Every open role lists the topics its interview covers, so you can prepare for the real thing rather than guessing.

See open roles