3. Question 3 When we are dealing with object detection, there are many different classifiers that we can use. Which of the following classifiers is trained on a large number…
4. Question 4 Consider the actual bounding box in red and the predicted bounding box in blue. What loss would you use to determine the performance of your model’s output?…
4. Question 4 Which of the following architecture solved the vanishing gradient problem by allowing the gradient to bypass different layers to improve performance? 1 point ImageNet VGGNet …
2. Question 2 Which of the following helps to reduce the number of parameters of an input image and still preserves the important features? 1 point Pooling Flattening …
1. Question 1 Which of these are a problem of sliding windows? Select all that apply 1 / 1 point Aspect Ratio Object sizes Overlapping objects Grayscale image …
1. Question 1 If we wanted to identify the cat in the image below, what kind of algorithm will we be working with? 1 / 1 point CV studio A Sliding…
5. Question 5 In object detection, the score: 1 / 1 point gives you the probability of each class is the confidence of the model prediction is the bounding box…
3. Question 3 Select the diagram that best demonstrates object detection model that uses a bounding box. 1 / 1 point
4. Question 4 Which of the following is not accurate about the AdaBoost? 1 / 1 point In an Adaboost, a strong classifier is a linear combination of a weak classifier …
2. Question 2 The following image with the bounding box is an example of 1 / 1 point Classification Object detection Filtering Classification+Localization
