Shared Visual Structure Makes Extra Source Data Helpful
Extra source images can improve a model when the source and target data share common visual patterns. For instance, a classifier trained on many park wildlife photos can learn features such as wing shapes, beaks, and body outlines. If a mobile app uses similar bird photos taken in parks and backyards, those learned features can be reused, so the larger source set helps the smaller target task instead of adding unrelated examples.
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
Shared Visual Structure Makes Extra Source Data Helpful
Source-Specific Features Can Consume Model Capacity
When is it reasonable to mix a large set of public web photos into a product-image training set?
A very large network trained long enough can, in principle, learn from two different image collections without an unavoidable tradeoff.
Complete the capacity requirement before adding more training data
Match each training-scenario element with its role in the learning argument.
Order the reasoning steps for deciding whether to add public web photos to training.
Why a larger model can learn from two image sources
Whether to Use 180,000 Public-Web Photos Alongside 4,000 App Photos
When is it reasonable to mix outside web images with app-captured images?
What does the 40:1 dataset ratio suggest in this example?
Combining a second image source always improves model performance.
Learn After
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.