regular questions about my background...
Computer Vision Engineer Interview Questions
735 computer vision engineer interview questions shared by candidates
Describe your research experience with this project
Explain briefly what is Bundle adjustment?
Why do you want to work at Meta?
- Write a function to produce the convolution of an image with a filter - Write a function that fills a buffer with a rolling set of image object segmentation results - From a set of loss functions like L2 loss or hinge loss, explain which ones are rotationally invariant, sensitive to rescalings of the input features, and which are convex. - Given a set of standard random forest trees and a set of gradient boosted trees, explain how the model's predictions would change if you remove the first tree, the last tree, or make other changes after training. - Talk about a system design you've worked on where a web service provides computer vision computations on input images. How did you test it? How did you deploy it? - Given a pandas DataFrame with some numeric columns, how to produce counts of data for different category IDs, including with or without extra processing to remove noisy, missing, or outlier data points.
Return true if a given Tree is a subtree of another Tree?
HR was basically behavioral questions. One was a coding round. A simple dynamic programming question of find the minimum cost in a 2D grid. One was a simple debugging round that checked your knowledge of shallow copy with lists in python and some tensorflow API question. One brain teaser. Given a shape how would you make two cuts and re-arrange into a perfect square. The final interviewer asked some sort of data flow diagram for Lukas kanade optical flow.
How do you design a system to detect a point cloud?
What are the matrices used in OpenGL? What are the special properties of a rotation matrix?
What is RANSAC used for?
Viewing 341 - 350 interview questions