* (-1,-0.95)
* (0.65, 0.2)
DISTANCE
Embedding on the
d-dimensional hypher-sphere
f(X) 2
2
= 1
0 = Identical
4 = As different as can be
d(P,Q) = f(P)−f(Q) 2
2
𝐿2 𝑁𝑜𝑟𝑚
FINDING THE RIGHT TRIPLETS
We need triplets that violate the equation to ensure fast convergance
𝑓 𝑎 − 𝑓(𝑝) - 𝑓 𝑎 − 𝑓(𝑛) + α ≤ 0
find P where argmax( 𝑓 𝑎 − 𝑓(𝑝) )
find N where argmin( 𝑓 𝑎 − 𝑓(𝑛) )
Triplet selection options
A) Generate triplets offline every N steps from a subset of data
B) Generate triplets online from a minibatch
Paper uses option B, with large minibatches with 1000s of examples
Classification with very few images
New people added all the time – don’t want to retrain
OneShot Learning
Common strategy for face verification, face identification, face clustering
Classification with very few images
New people added all the time – don’t want to retrain
OneShot Learning
Common strategy for face verification, face identification, face clustering
Pairs of input and 1 or 0 as output – try to minimize distance of 1s (same) and maximize distance of 0s (different)
assumes it will generalize
1000 of features in embedding