Questions tagged [one-shot-learning]
The one-shot-learning tag has no usage guidance.
7
questions with no upvoted or accepted answers
2
votes
0answers
30 views
Few shot learning and object detector
I have a dataset with a lot of classes (~10000+) but few examples by classes (~15-). I want to classify these classes, but there are some specificities. My examples provide from a video stream. ...
2
votes
2answers
306 views
Why does Siamese neural networks use tied weights and how do they work?
Reading this paper on one-shot learning "Siamese Neural Networks for One-shot Image Recognition" I was introduced to the idea of Siamese Neural Networks.
What I did not fully grasp was what they ...
1
vote
1answer
19 views
Should number of classes be the same in few shot learning train and test?
I used to believe in k-way-n-shot few-shot learning, k and n (number of classes and samples from each class respectively) must be the same in train and test phases. But now I come across a git ...
1
vote
0answers
83 views
Source to learn/understand one-shot learning
I'm currently looking into one-shot learning and I wonder if there are any good sources/tutorials out there, which demonstrate one-shot learning in a (more or less) "hands-on" way?
Also some hints ...
0
votes
0answers
14 views
SSD-300 tensorflow mAP is very low due to unstable loss
I am training my SSD-300 model for which I have resized images to 300x300. I am using the default settings as mentioned in github repo:
https://github.com/balancap/SSD-Tensorflow
The loss is unstable ...
0
votes
0answers
54 views
Siamese Network for face comparison wont learn, accuracy stuck on 0.5, and loss stuck too
I'm trying to train a siamese network which contains a CNN and an embedding layer at the end to yield 2 similar (close) vectors for 2 images of the same person.
I'm using the LFW_Cropped dataset, and ...
0
votes
1answer
428 views
Should I normalise image pixel wise for pretrained VGG16 model
My goal is to use pretrained VGG16 to compute the feature vectors excluding the top layer. I want to compute embedding(no training involved) per image one by one rather than feeding batches to the ...
