Computer Vision Interview Questions for Data Science
30 Computer Vision questions with answers for data science roles — 9 easy, 14 medium, 7 hard.
About Computer Vision
Computer vision interviews cover how machines understand images and video: convolutions, classification, object detection, segmentation and vision transformers. Expect metrics like IoU and mAP, coding tasks with OpenCV, PyTorch and NumPy, and scenarios on class imbalance, domain shift, labelling quality and running models fast on edge devices. Practical judgement about data matters as much as architecture knowledge.
Sheet progressStart practicing
3 QUESTIONS FREESign up to unlock the full question bank and track your progress.Unlock every question and answer, then continue practising company-wise and package-wise.
✓ 3 questions free • Unlock the rest in seconds
01
How is an image represented for a deep learning model?
An image is a numeric array of height by width by channels, where a colour image has three channels, usually RGB, with pixel values from 0 to 255. Libraries differ: OpenCV loads BGR in HWC order, while PyTorch expects tensors in CHW order with a batch dimension in front. Before training you convert to float, scale to 0-1 and normalise with the mean and standard deviation used by the pretrained model.
02
What do kernel size, stride and padding mean in a convolution layer?
The kernel is a small learnable filter, such as 3x3, that slides over the image and computes a weighted sum at each position. Stride is how many pixels it moves each step; stride 2 halves the output size. Padding adds border pixels so the output can keep the same size and edge pixels get processed. Output size equals (input minus kernel plus 2 times padding) divided by stride, plus one.
Pooling downsamples a feature map by summarising small regions. Max pooling keeps the largest value in each window, such as 2x2, and average pooling keeps the mean. It reduces computation, enlarges the receptive field of later layers and gives a little tolerance to small shifts. Many modern networks replace pooling with strided convolutions, but global average pooling before the classifier head is still very common.
04
What is the difference between image classification, object detection and image segmentation?
Classification assigns one label to the whole image, such as cat. Object detection finds each object and returns a bounding box plus a class label and confidence for each one. Segmentation labels every pixel, giving exact object shapes. The tasks need increasingly detailed annotations and compute. Choose based on the business need: counting products on a shelf needs detection, while measuring a crack's area needs segmentation.
IoU measures how well a predicted box or mask overlaps the ground truth. It is the area of their intersection divided by the area of their union, giving a value from 0 for no overlap to 1 for a perfect match. In detection, a prediction usually counts as correct if IoU is at least 0.5 with a ground truth box of the same class. IoU is also used inside non-maximum suppression.
06
What is non-maximum suppression in object detection?
A detector usually predicts many overlapping boxes for the same object. Non-maximum suppression keeps the box with the highest confidence, removes other boxes of the same class whose IoU with it exceeds a threshold such as 0.5, and repeats with the remaining boxes. A threshold that is too low can delete genuinely nearby objects in crowded scenes, so variants like soft-NMS lower scores instead of removing boxes.
07
Annotators labelling your images often disagree with each other. How do you handle this?
First measure agreement, for example with Cohen's kappa or IoU between annotators' boxes, to find which classes are confusing. Usually the guidelines are unclear, so write precise rules with example images for edge cases and retrain annotators. Have multiple people label a subset and resolve conflicts by majority vote or an expert reviewer. Track ambiguous images separately, since even a perfect model cannot beat human label noise.
08
Write OpenCV code to read an image, convert it to grayscale, resize it and detect edges.
Semantic segmentation gives each pixel a class, such as road or car, but does not separate two cars. Instance segmentation separates individual objects of countable classes, giving each car its own mask. Panoptic segmentation combines both: every pixel gets a class, and countable objects also get an instance ID, while background stuff like sky stays semantic. Autonomous driving and robotics often need panoptic or instance output.
11
What is mean Average Precision (mAP) in object detection?
For each class, detections are ranked by confidence and a precision-recall curve is computed, where a detection is a true positive if its IoU with an unmatched ground truth box passes a threshold. Average Precision is the area under that curve. mAP is the mean across classes. mAP@0.5 uses IoU 0.5, while mAP@0.5:0.95 averages over thresholds from 0.5 to 0.95 and rewards tighter boxes.
12
How do one-stage and two-stage object detectors differ?
Two-stage detectors, like Faster R-CNN, first propose candidate regions and then classify and refine each one, which gives strong accuracy, especially for small objects, but is slower. One-stage detectors, like YOLO and SSD, predict boxes and classes directly over a dense grid in a single pass, making them fast enough for real-time video. Modern one-stage models have closed most of the accuracy gap, so they dominate edge and video use cases.
The receptive field is the region of the input image that can influence one activation. Early layers see small patches like edges, and deeper layers see larger regions, enabling recognition of whole objects. It grows with kernel size, depth, stride and pooling, and dilated convolutions increase it without extra parameters. If the receptive field is smaller than the objects you care about, the network cannot capture their full context.
14
Why do residual connections make very deep networks easier to train?
A residual block adds its input to its output, so the layers learn a residual F(x) and the block outputs F(x) plus x. If extra layers are not useful, they can learn to output near zero and the block behaves like identity. The skip path also lets gradients flow directly to early layers, reducing vanishing gradients. This is why ResNets with 50 or 100-plus layers train well where plain deep networks degrade.
15
What is U-Net and why is it popular for segmentation?
U-Net is an encoder-decoder network. The encoder downsamples to capture context, and the decoder upsamples back to full resolution to produce a per-pixel mask. Skip connections copy encoder feature maps to the matching decoder level, so fine spatial detail lost during downsampling is recovered. It works well with limited labelled data, which made it the standard for medical imaging and industrial defect segmentation, and it is also the backbone of many diffusion models.
16
You are building defect detection for a factory line where only 1 in 1,000 images shows a defect. How do you approach it?
With so few defects, a plain classifier will learn to say no defect. Collect every defect image possible and oversample them or use class-weighted or focal loss. Consider anomaly detection trained only on good parts, which flags anything unusual. Use augmentation that mimics real variation in lighting and position. Evaluate with recall at a fixed false alarm rate, since missing a defect usually costs far more than a manual recheck.
17
Your product image classifier works on studio catalogue photos but fails on photos users take with their phones. Why, and what do you do?
This is domain shift: user photos have clutter, blur, poor lighting and odd angles that the model never saw. Collect and label a sample of real user photos and evaluate on them separately. Add augmentation for blur, noise, colour jitter, rotation and random crops, and fine-tune on a mix of studio and real images. Monitor accuracy on user photos in production, since that is the distribution that matters.
18
Your classifier scores 98 percent on validation, but Grad-CAM shows it focuses on a watermark rather than the object. What is happening?
The model has learned a shortcut: the watermark correlates with the label in your dataset, perhaps because images of one class came from a single source. It will fail when that correlation breaks. Remove or crop the watermarks, rebalance sources across classes, and create a validation set from different sources. Keep using saliency maps and slice-based evaluation to catch other spurious cues such as backgrounds or text.
19
You need to extract fields from scanned invoices that come in hundreds of different layouts. How would you design it?
Fixed templates will not scale to hundreds of layouts. Start with preprocessing: deskew, denoise and detect text regions. Run OCR to get words with their positions. Then use a layout-aware document model, or a vision-language model, to map words to fields like invoice number, GSTIN and total. Add validation rules, such as GSTIN format and line items summing to the total, and send low-confidence documents to human review.
20
Write a Python function to compute IoU between two bounding boxes given as (x1, y1, x2, y2).
import torch, torch.nn as nn
from torchvision import models
model = models.resnet18(weights=models.ResNet18_Weights.DEFAULT)
for p in model.parameters():
p.requires_grad = False # freeze backbone
model.fc = nn.Linear(model.fc.in_features, 5)
opt = torch.optim.AdamW(model.fc.parameters(), lr=1e-3)
loss_fn = nn.CrossEntropyLoss()
# train head first, then unfreeze later layers with a lower lr
22
Write NumPy code to compute the Dice coefficient between a predicted and a true binary mask.
Situation: a shelf-detection model plateaued at low accuracy. Task: find out why and fix it. Action: I reviewed 500 errors and found that a third were labelling mistakes, with inconsistent boxes for partly hidden products. I rewrote the guidelines with visual examples, had a second annotator review hard images and relabelled the worst batch. Result: mAP rose by 9 points without changing the model, and labelling rework dropped sharply.
A Vision Transformer splits an image into fixed patches, such as 16x16, flattens each into a token embedding, adds position embeddings and processes them with self-attention. Every patch can attend to every other patch from the first layer, giving global context. CNNs have built-in locality and translation biases, so they learn well from smaller datasets. ViTs need more data or strong pretraining but scale very well and are now common backbones.
25
What are anchor boxes, and why have anchor-free detectors become popular?
Anchor boxes are predefined boxes of several sizes and aspect ratios placed at each grid location; the detector predicts offsets from them and a class score. They need careful tuning to match object shapes in your data and create many redundant predictions. Anchor-free detectors, such as FCOS-style or centre-point methods, predict object centres and box sizes directly. They have fewer hyperparameters, generalise better to unusual shapes and simplify the pipeline.
26
What is a contrastive image-text model like CLIP, and how does it enable zero-shot classification?
CLIP trains an image encoder and a text encoder together on hundreds of millions of image-caption pairs, pulling matching pairs close in a shared embedding space and pushing mismatches apart. For zero-shot classification you embed prompts like 'a photo of a damaged parcel' for each class and pick the class whose text embedding is most similar to the image embedding. It works without task-specific training but may need fine-tuning for niche domains.
27
Your detector finds large objects well but misses small objects like distant people. How do you improve it?
Small objects lose detail after downsampling. Train and infer at higher input resolution, or tile large images into overlapping crops. Use a backbone with a feature pyramid so detection happens on high-resolution maps. Tune anchors or assignment settings for small sizes, and oversample images with small objects. Check labelling quality for tiny boxes too. Measure mAP on small objects separately to confirm improvement.
28
You must run object detection on an edge camera at 30 frames per second. How do you meet that target?
Start with a lightweight one-stage detector at the smallest input size that keeps acceptable accuracy. Optimise it: export to ONNX, then use a hardware runtime like TensorRT or OpenVINO, with FP16 or INT8 quantisation calibrated on real images. Prune or distil from a larger model if needed. Profile the full pipeline, including decoding and preprocessing, and run detection every few frames with tracking in between if compute is tight.
29
You have 50,000 unlabelled images and budget to label only 3,000. How do you use the budget well?
Do not pick 3,000 at random. Label a small diverse seed set, using embedding clustering to cover variety, and train a first model. Then use active learning: label the images the model is least confident about or that disagree across models. Use semi-supervised methods like pseudo-labelling high-confidence images, or self-supervised pretraining on all 50,000. Keep a randomly sampled test set so evaluation stays unbiased.
30
Write NumPy code for non-maximum suppression on a set of boxes and scores.
import numpy as np
def nms(boxes, scores, thr=0.5):
x1, y1, x2, y2 = boxes.T
areas = (x2 - x1) * (y2 - y1)
order = scores.argsort()[::-1]
keep = []
while order.size:
i = order[0]
keep.append(i)
w = np.maximum(0, np.minimum(x2[i], x2[order[1:]]) - np.maximum(x1[i], x1[order[1:]]))
h = np.maximum(0, np.minimum(y2[i], y2[order[1:]]) - np.maximum(y1[i], y1[order[1:]]))
inter = w * h
iou = inter / (areas[i] + areas[order[1:]] - inter)
order = order[1:][iou < thr]
return keep
Frequently asked questions
How important is Computer Vision in Data Science interviews?
Computer vision interviews cover how machines understand images and video: convolutions, classification, object detection, segmentation and vision transformers. Expect metrics like IoU and mAP, coding tasks with OpenCV, PyTorch and NumPy, and scenarios on class imbalance, domain shift, labelling quality and running models fast on edge devices. Practical judgement about data matters as much as architecture knowledge.
How should I use the Computer Vision sheet?
Go top to bottom — easy to hard. Answer before opening each answer, tick what you solved and save misses to Last-Minute Revision.