Skip to content
tezvyn:

Computer Vision

Image/video models, diffusion, OCR, multimodal

71 bites

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

Easy everything in Computer Vision

easy1 min read

Precision vs recall in object detection.

Precision is fraction of detections that are correct, recall is fraction of true objects found; prioritize recall for safety-critical detection, precision when false alarms are costly.

easy1 min read

What data augmentations help small image datasets?

Apply label-preserving transforms like flips, crops, rotation, color jitter, and mixing to enlarge effective data and reduce overfitting.

easy1 min read

Outline the classic image stitching pipeline.

Detect and match features like SIFT, estimate a homography with RANSAC, warp and blend with multiband or feathering.

easy1 min read

How do you build an HDR image from bracketed exposures?

Align frames, recover the camera response function, merge to a linear radiance map weighted by exposure, then tone map for display.

easy2 min read

Leveraging unlabeled data with limited labels

Pretrain a representation on the million unlabeled images via self-supervision, then fine-tune on the 1,000 labels; or use pseudo-labeling and consistency regularization.

easy2 min read

Transfer learning from ResNet50 on small data

Replace the final classification head with one sized to your classes, freeze the pretrained convolutional backbone as a feature extractor, train the new head, then optionally fine-tune top blocks at a low…

easy2 min read

Designing a baseline Visual Question Answering model

Encode the image with a CNN, encode the question with an RNN or embedding, fuse the two vectors, and classify over a fixed answer vocabulary.

easy2 min read

Semantic, instance, and panoptic segmentation

Semantic labels every pixel by class without separating objects; instance separates individual objects but may skip background; panoptic unifies both, labeling stuff and distinct thing instances.

easy2 min read

Diffusion forward and reverse processes

Forward process gradually adds Gaussian noise until data is pure noise; reverse process learns to denoise step by step; the network predicts the noise added at each timestep.

easy1 min read

GAN architecture: generator and discriminator roles

Generator maps noise to fake samples, discriminator classifies real versus fake, they train as a two-player game until samples fool the discriminator.

easy1 min read

Self-attention over image patches explained

Each patch projects to query, key, value; a patch's query is scored against all keys, softmax-normalized into weights, used to combine all values.

easy2 min read

How ViT and CNN process an image differently

A CNN slides local filters over the raw pixel grid; a ViT splits the image into patches, flattens and linearly embeds each into a token, adds positional embeddings, and feeds the sequence to…

easy1 min read

Design a tracking-by-detection tracker

Detect per frame, then associate boxes across frames by IoU or appearance using Hungarian matching, maintaining track ids.

easy1 min read

Sparse vs dense optical flow and Lucas-Kanade

Sparse flow tracks selected feature points, dense flow computes a vector per pixel; Lucas-Kanade solves brightness constancy in a local window assuming constant motion.

easy1 min read

Semantic versus instance segmentation

Semantic segmentation labels each pixel by class but merges objects of the same class; instance segmentation also separates individual objects.

easy2 min read

Mean Average Precision in object detection

AP is the area under the precision-recall curve per class; mAP averages AP over classes, and COCO also averages over IoU thresholds.

easy1 min read

Intersection over Union for detection

IoU is the area of overlap divided by the area of union of predicted and ground-truth boxes; a threshold decides true positives.

easy1 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.

easy1 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.

easy1 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.

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