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.