Learn Before
Adding Simulated Motion Blur to Cat Images
When dev-set cat images have more motion blur, non-blurry training images can be modified by adding simulated motion blur so that they are more similar to the dev set.
0
1
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Machine Learning Yearning @ DeepLearning.AI
Related
Synthesizing In-Car Speech Audio from Quiet Speech and Road Noise
Adding Simulated Motion Blur to Cat Images
Computer Realism Challenge in Artificial Data Synthesis
Getting Synthetic Data Details Close Enough to the Real Distribution
What does artificial data synthesis primarily enable you to create in relation to your dev set?
True or False: Artificial data synthesis can help you build a large training dataset that reasonably matches your dev set.
Artificial data synthesis allows you to create a _____ that reasonably matches the dev set.
What is the primary benefit of artificial data synthesis when your training set does not match the dev set?
Artificial data synthesis always produces data that perfectly replicates the real-world distribution of the dev set.
Artificial data synthesis allows the creation of a _____ dataset that reasonably matches the dev set.
Match each artificial data synthesis scenario to the real-world factor it introduces into training data.
Order the reasoning steps for deciding whether artificial data synthesis can close a train/dev distribution gap.
According to Machine Learning Yearning, in which broad situation is artificial data synthesis most directly applicable?
Artificial data synthesis can be used to bridge the gap between the training set distribution and the dev set distribution.
Machine Learning Yearning states there are several _____ where synthesis allows creation of a huge dataset matching the dev set.
Match each key concept in artificial data synthesis to its correct definition.
Order the steps for synthesizing in-car speech audio to match a dev set recorded in moving vehicles.
Under what conditions is artificial data synthesis a viable approach to align training data with the development set?
Evaluating the feasibility of artificial data synthesis for a specialized validation set
Name the two primary goals of artificial data synthesis when training and dev distributions differ
Learn After
In the cat image detector example, why do dev set images tend to have more motion blur than training images?
True or False: Adding simulated motion blur to non-blurry training images can reduce the distribution mismatch between training and dev sets.
To make training images more similar to a dev set with motion blur, you can add simulated _____ to non-blurry training images.
Why is simulated motion blur added to non-blurry training images in the cat detector example?
Motion blur in dev-set cat images is caused by cellphone users slightly moving their phone while taking pictures.
To close the distribution gap in the cat detector, you add _____ to non-blurry training images.
Match each dataset or image source to its characteristic in the cat detector example.
Order the steps to apply simulated motion blur to improve a cat detector's performance on a blurry dev set.
What specific distribution gap does adding simulated motion blur to training images address in the cat detector example?
Internet images used as cat detector training data typically have the same level of motion blur as cellphone-captured dev-set images.
In the cat detector example, the non-blurry training images that receive simulated blur originally come from _____ images.
Match each observation in the cat detector scenario to the corresponding explanation or action.
Order the reasoning steps that lead to the decision to use simulated motion blur as an artificial data synthesis technique.
Write an essay explaining how simulated motion blur helps align cat detector datasets
Diagnose and resolve the dataset distribution gap in a mobile cat detector
Explain why simulated motion blur is added to clear training images