The Necessity and Pitfall of Augmentation in Deep Learning: Observations During a Case Study in Triplet Learning for Coin Images.

Published in: ICPRAM (2020)

Keyphrases

deep learning
deep architectures
unsupervised learning
image database
learning algorithm
reinforcement learning
learning process
online learning
supervised learning
image classification
unsupervised feature learning
weakly supervised
test images
input image
image features
feature extraction
co occurrence
maximum likelihood
natural images
probabilistic model
image regions
active learning
lighting conditions
image annotation
multiple images
image retrieval
object recognition
computer vision