Website Images and Mobile Phone Pictures as a Distribution Mismatch Example
In the cat app example, a classifier trained and tested on website images performs poorly after deployment because user-uploaded mobile-phone pictures have a different look, such as lower resolution, blurrier images, and poor lighting.
0
1
References
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Tags
Machine Learning
Deep Learning
Machine Learning Strategy
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Yearning @ DeepLearning.AI
Related
Avoid Randomly Shuffling Mixed-Source Data into Dev/Test Sets
Include Some Target-Distribution Examples in Training Alongside Auxiliary Data
Down-Weighting Auxiliary Data from a Different Distribution
Training Dev Set
Error Table Across Two Data Distributions and Three Error Types
Data Mismatch Between Training and Dev Set Distributions
Limited Practical Scope of Domain Adaptation for Different Data Distributions
Domain Adaptation for Different Data Distributions
Website Images and Mobile Phone Pictures as a Distribution Mismatch Example
Random 70/30 Train/Test Split Can Fail Under Distribution Shift
Which data should define the dev and test sets for the cat-picture app?
Dev and test sets should represent the future data distribution of interest.
Complete the principle: Dev and test sets should reflect _____ data.
Match each cat-app data group with its appropriate role or property.
Order the decisions for building datasets when auxiliary and target data differ.
Explain why different training and evaluation distributions can be appropriate.
Diagnose the evaluation-set mistake in a mobile cat-classification app.
Why did success on website images fail to ensure success on mobile uploads?
Which dataset design best uses both target and auxiliary cat images?
Using extra internet images for training requires internet images in dev and test sets.
Learn After
Why did the deployed cat detector perform poorly despite doing well on its original test set?
The original test set accurately represented the mobile-phone pictures encountered after deployment.
The classifier failed to generalize to the actual distribution of _____ pictures.
Match each part of the cat app example to its role in the distribution mismatch.
Order the events that revealed the cat detector's distribution mismatch.
Explain why strong website-image test performance did not predict success in the mobile app.
Diagnose a cat detector that succeeds on website images but fails on app uploads.
What three characteristics distinguished user-uploaded pictures from the website images?
What did the detector's strong result on the website-based test set actually demonstrate?
Using website images for both training and testing can hide poor generalization to user-uploaded mobile-phone pictures.