Back to AI/ML & Deep Learning
Curated
Interview series
Computer Vision Tasks
AI/ML & Deep Learning

Computer Vision: Detection, Segmentation & Beyond Classification

TechnicalMedium~30 minDesigned by experts

About this interview

A technical interview on Computer Vision Tasks, pitched at the medium level. A voice AI interviewer leads the conversation, adapts its questions to your answers, keeps you on topic, and afterward gives you honest, specific feedback on where you were strong and where to improve. Expect roughly 30 minutes.

What you'll be assessed on

Explain object detection approaches (two-stage R-CNN family vs one-stage YOLO/SSD) and the role of anchors and NMS
Describe semantic vs instance vs panoptic segmentation and representative architectures
Define detection/segmentation metrics (IoU, mAP) and how they're computed
Reason about real-time vs accuracy trade-offs in a vision pipeline

Topics covered

IoU and metricsNMS and post-processingAnchors and region proposalsTwo-stage detectorsDetection paradigmsOne-stage detectorsFeature pyramids and multi-scaleAnchor-free detectionSegmentation typesSegmentation architecturesSegmentation metricsInstance segmentationMulti-scale and real-world challengesTraining challenges

A few sample questions

Just examples to set expectations - the real interview has many more and adapts to your responses.

In object detection, what does Intersection over Union actually measure, and why is it the right metric for comparing a predicted bounding box to a ground-truth box?
Compare one-stage detectors like SSD and YOLO against two-stage detectors like Faster R-CNN. What does each family trade for its advantage?
How does Mask R-CNN extend Faster R-CNN to produce instance segmentation masks? What head does it add and how does it interact with the detection head?

Related interviews

Junior
AI/ML & Deep Learning

Bias-Variance Tradeoff & Regularization

Technical·~30 min
Junior
AI/ML & Deep Learning

Supervised Learning Algorithms

Technical·~30 min
Mid
AI/ML & Deep Learning

Tree-Based & Ensemble Methods

Technical·~30 min
Mid
AI/ML & Deep Learning

Unsupervised Learning & Dimensionality Reduction

Technical·~30 min
Mid
AI/ML & Deep Learning

CNN Architecture & Computer Vision Fundamentals

Technical·~30 min
Senior
AI/ML & Deep Learning

Deep Generative Models: GANs & VAEs

Technical·~30 min
Mid
AI/ML & Deep Learning

Feature Engineering & Data Preparation

Technical·~30 min
Senior
AI/ML & Deep Learning

Generative Models: Diffusion vs Autoregressive

Technical·~30 min
Senior
AI/ML & Deep Learning

Vision-Language Models & Multimodal AI

Technical·~30 min
Senior
AI/ML & Deep Learning

Graph Neural Networks

Technical·~30 min
Mid
AI/ML & Deep Learning

Decoding Strategies & In-Context Learning

Technical·~30 min
Junior
AI/ML & Deep Learning

Linear Algebra & Mathematical Foundations for ML

Technical·~30 min