Skip to content
tezvyn:

Computer Vision

Image/video models, diffusion, OCR, multimodal

135 bites

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

Interview questions in Computer Vision, page 3

advanced1 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.

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

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.

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.

advanced2 min read

Focal Loss and class imbalance in detectors

Focal loss multiplies cross-entropy by a (1-p)^gamma factor that down-weights easy, well-classified examples so the vast easy background does not swamp the loss.

advanced2 min read

Deploying real-time detection on edge devices

Pick an efficient one-stage detector, train with augmentation, then quantize, prune, and compile to a hardware-accelerated runtime, measuring latency and accuracy tradeoffs.

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.

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.

intermediate1 min read

U-Net architecture and its skip connections

U-Net has a contracting encoder, an expanding decoder, and skip connections that concatenate matching-resolution encoder features into the decoder to recover spatial detail lost in downsampling.

intermediate1 min read

How does Mask R-CNN do instance segmentation?

Faster R-CNN backbone plus RPN, then RoIAlign and a parallel mask head predicting per-class binary masks.

intermediate1 min read

How to improve coarse segmentation boundaries?

Skip connections and higher-resolution features, boundary-aware losses, and point-based or CRF refinement.

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.

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.

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

Design a tracking-by-detection tracker

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

intermediate1 min read

Brightness constancy and small-motion assumptions

Brightness constancy says a point's intensity is invariant under motion; small motion lets you linearize via Taylor expansion.

intermediate1 min read

Kalman filter for bounding-box tracking

State, transition, measurement models, and process plus measurement noise; predict then correct each frame. State holds box position and velocity; measurement is the detected box.

intermediate1 min read

3D CNNs vs two-stream action recognition

3D CNNs learn spatiotemporal filters end to end but are heavy; two-stream splits RGB appearance and precomputed optical flow, strong but costly to compute flow.

intermediate1 min read

Re-identification in multi-object tracking

Re-ID matches an object to its prior id using appearance embeddings, not just position; store track features and match re-entering detections by embedding similarity.

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.

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