Questions tagged [triplet-loss]

Triplet losses are defined in terms of the contrast between three inputs. Each of the inputs has an associated class label, and the goal is to map all inputs of the same class to the same point, while all inputs from other classes are mapped to different points some distance away. It's called a triplet because the loss is computed using an anchor, a sample belonging to the same class as the anchor, and a sample belonging to a different class.

Filter by
Sorted by
Tagged with
0
votes
0answers
13 views

speaker recognition: training on enrollment data

I'm working on a speaker recognition challenge. I have already trained my model on the voxceleb2 dataset in triplet setup. Now, for the challenge, I have two sets. enrollment (1 audio/subject) [IDs ...
1
vote
0answers
118 views

Resnet model does not train with triplet loss, while VGG16 is able to train, why?

I am trying to do a transfer learning with ResNet50V2 model using triplet loss function. I have kept Include_top = False, input shape = (160,160,3) with Imagenet weights. The last 3 layers of my model ...
1
vote
0answers
48 views

Why are we interested in gradient with respect to input?

I am learning about sampling methods for Deep Embedding Learning. I was reading an article named: "Sampling Matters in Deep Embedding Learning" (https://arxiv.org/abs/1706.07567). In the ...
3
votes
1answer
3k views

In training a triplet network, I first have a solid drop in loss, but eventually the loss slowly but consistently increases. What could cause this?

I haven't even finished 1 epoch, so I don't think it could any sort of overfitting. I am training on a very large amount of data (27 gb of text) so it'll still be a while before I even reach one epoch....
0
votes
0answers
20 views

Is there any algorithms/models to generate embedings of sequential data (other than RNN)?

I know that RNN can be used for such task. For instance facenet used rnn with triplet loss. But maybe there are some less sophisticated alternatives to try first?
2
votes
1answer
62 views

Learning useful semantic representations of data

Training a neural network on its final task (e.g. classification) right from the beginning is not always the best way to go. I'd like to make a short list of recognized methods of motivating a NN to ...
0
votes
0answers
186 views

Replacement for angular distance metric

I am looking for a distance metric that could be used instead of cosine/angular distance for high dimensional data. Metric that is limited the same way as cosine/angular distance is would be great. ...
2
votes
1answer
102 views

Maximizing AUC based on point cloud distance

Let $V$ be an $n$ dimensional space with sets of positive class vectors $P$ and negative class vectors $N$. The task is to find a vector $x$ such that AUC is maximized, based on ranking generated by ...
0
votes
2answers
845 views

Why the Triplet Loss function distincts anchor and positive?

I read the paper and I understand that anchoring one image and select corresponding semi-hard positives and negatives is an efficient way of generating samples. However, I don't understand why the ...
3
votes
1answer
692 views

Facenet: Using Ensembles of Face Embedding Sets

The Facenet is a deep learning model for facial recognition. It is trained for extracting features, that is to represent the image by a fixed length vector called embedding. After training, for each ...
1
vote
2answers
1k views

Does triplet loss help for document similarity search?

I build CNN network over documents with triplet loss. And compare documents with cosine similarity. It does really find similar docs and catches interesting dependencies. But simple tfidf model does ...
1
vote
1answer
412 views

Overcome underfitting on train data using CNN architecture

I use 2 layer CNN network for NLP task with triplet loss with margin 0.2. The task is to learn document embeddings to find similar docs. My architecture is similar to this https://arxiv.org/abs/1406....
4
votes
0answers
1k views

Triplet Deep Learning Embedding Loss Functions

Triplet embeddings consist of mapping a group of images to an embedding space, such that images deemed more similar to each other end up closer together. The "triplet" comes from training, where we ...
6
votes
1answer
2k views

How does FaceNet (Google's facerecognition) handles a new image?

I am currently researching in the facerecognition field. And I can not understand how the facenet algorithm handels a new image They use an euclidean space for image representation. Which means that ...