Machine Learning Computer Vision 5

Question 1

What is panoptic segmentation?

Accepted Answer

A unified task combining semantic segmentation of background stuff and instance segmentation of foreground things

Answer

Panoptic segmentation unifies semantic segmentation (for background regions) and instance segmentation (for countable objects) into a single coherent output.

Question 2

Which attention mechanism in Vision Transformers (ViT) allows the model to relate different patches of an image to each other?

Accepted Answer

Self-attention

Answer

Self-attention computes relationships between all pairs of image patches, enabling ViT to capture long-range dependencies without convolutions.

Question 3

What is image super-resolution in deep learning?

Accepted Answer

Reconstructing a high-resolution image from a low-resolution input

Answer

Super-resolution models learn to reconstruct fine details and textures in high-resolution outputs from coarse low-resolution inputs.

Question 4

In stereo vision, what is a disparity map used to compute?

Accepted Answer

Depth information from two horizontally offset cameras

Answer

Disparity (the horizontal shift of corresponding pixels between left and right camera images) is inversely proportional to depth, enabling 3D reconstruction.

Question 5

What does mean Average Precision (mAP) measure in object detection evaluation?

Accepted Answer

The average of per-class Average Precision scores across multiple IoU thresholds and classes

Answer

mAP aggregates the area under the precision-recall curve for each class and averages across all classes and IoU thresholds, providing a comprehensive detection metric.

Machine Learning Practice Test

Machine Learning Practice Test

Machine Learning Computer Vision 5