Why can examples from one photo source help train on another?
Question: In one to three sentences, explain why product photos taken in a studio can still help train a model that will be used on customer-uploaded phone photos.
Sample answer: Because studio photos and phone photos still share many visual patterns, such as object shapes, colors, and textures, the model can reuse features learned from the studio images when processing phone photos. That shared structure makes the extra studio data useful even though the two sources are not identical.
Key points:
- Shared visual patterns across the two photo sources
- Feature knowledge learned from one source can transfer to the other
Rubric: Full credit for stating both the shared patterns and the transfer of learned features between the two sources; partial credit for only saying that more examples help without explaining why the transfer works.
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
Why can a model trained on street-level dog photos still help on pet-app photos?
True or False: Adding more web images can give a classifier more examples of what a bicycle can and cannot look like.
Online store photos and customer-submitted photos share some _____.
Match each component to its role in transferring knowledge from a broad source set to a target app.
Arrange the reasoning behind why extra catalog photos can improve a product classifier for a shopping app.
Why can catalog photos help a model trained for shopper photos?
Why adding web photos can improve a plant-identification app
Why can examples from one photo source help train on another?
What is a likely result of adding 20,000 extra online photos to improve a traffic-sign classifier?
True or False: A neural network trained on photos from a document scanner can still transfer useful features to similar photos taken with a phone camera.