NEW
Font size
WorksheetsCNN_YOLO_Module_5
Total questions: 20
Worksheet time: 10mins
In CNN, which layer is responsible for extracting features from the image?
Pooling layer
Convolutional layer
Fully connected layer
Output layer
What does a kernel/filter do in a convolution operation in CNN?
It adds noise to the image
It processes the image in patches
It divides the image into sections
None of the above
What is the purpose of the pooling layer in CNN?
Reduces the dimensionality of the data
Increases the image size
Adds noise to the data
None of the above
Which of the following is true about YOLO?
It detects objects in images in a single pass
It requires multiple passes to detect objects
It only works with small images
None of the above
In YOLO, how is an image divided for object detection?
Into random sections
Into a grid of cells
Into layers of color channels
None of the above
What does YOLO output after detecting objects?
A list of coordinates
Bounding boxes with class labels
Only the class labels
None of the above
What is the advantage of YOLO compared to other object detection models?
It is very fast and accurate
It processes the entire image at once
It is easier to train, deploy, and optimize for real-time applications
All of the above
In a CNN, what is the purpose of the fully connected layer?
To connect the image input to the network
To reduce the image size
To combine all features extracted from the convolutional layers
None of the above
Which algorithm does YOLO use for object classification and detection?
Decision Trees
Convolutional Neural Networks (CNN)
K-Nearest Neighbors
Linear Regression
Which of the following best describes the architecture of YOLO?
YOLO uses a single convolutional network for object classification and localization
YOLO uses multiple networks for object detection
YOLO works by scanning the image with multiple sliding windows
YOLO detects objects by using region proposal networks
In YOLO, what does each grid cell predict?
Only the class of the object
Only the location of the object
Both the class and location of the object
Only the number of objects in the image
What do CNN and YOLO stand for?
Convolutional Network Layer and You Only Learn Once
Convolutional Neural Layer and Your Object Locator Output
Convolution Neural Link and You Only Look One-way
None of the above
Which of the following manufacturing applications falls under image classification?
Predicting machine failure based on vibration data
Identifying defective products on an assembly line
Predicting demand for raw materials
Monitoring temperature changes in machines
Which of the following manufacturing applications falls under object detection?
Identifying when a product is out of stock in the warehouse
Detecting the types on products among the objects moving on the conveyor
Calculating machine efficiency
Estimating the lifetime of a product based on wear and tear
In which scenario would you typically choose Deep Learning (DL) over Machine Learning (ML)?
When you have a small, labeled dataset
When you are working with unstructured data like images or text
When you are working with simple linear relationships
When the dataset contains only numeric values
What is the role of the Backbone in the YOLO architecture?
It predicts the class of the detected objects
It extracts features from the input image
It performs the bounding box regression
It removes noise from the image
What is the main function of the Head in the YOLO architecture?
To extract features from the image
To predict the class labels and bounding box coordinates for the detected objects
To resize the input image
To apply filters on the image
Which of the following is the primary task of image classification?
Identifying specific objects within an image
Labeling an image with a single class or category
Drawing bounding boxes around detected objects
Dividing an image into multiple regions for segmentation
What is the main difference between object detection and image classification?
Object detection only works with grayscale images, while image classification works with color images
Object detection involves identifying and localizing multiple objects in an image, while image classification only assigns one label to the entire image
Object detection only works on static images, while image classification works on video
Object detection requires manual feature extraction, while image classification uses neural networks
Which of the following tasks would require object detection instead of image classification?
Classifying an image as a cat or dog
Identifying the location and size of a person in a photo
Recognizing a face in an image
Detecting the color of an object in an image
