Vector Embeddings with Subvector Permutation Invariance using a Triplet Enhanced Autoencoder

11/18/2020
by   Mark Alan Matties, et al.
0

The use of deep neural network (DNN) autoencoders (AEs) has recently exploded due to their wide applicability. However, the embedding representation produced by a standard DNN AE that is trained to minimize only the reconstruction error does not always reveal more subtle patterns in the data. Sometimes, the autoencoder needs further direction in the form of one or more additional loss functions. In this paper, we use an autoencoder enhanced with triplet loss to promote the clustering of vectors that are related through permutations of constituent subvectors. With this approach, we can create an embedding of the vector that is nearly invariant to such permutations. We can then use these invariant embeddings as inputs to other problems, like classification and clustering, and improve detection accuracy in those problems.

READ FULL TEXT
research
02/16/2022

Cross-Modal Common Representation Learning with Triplet Loss Functions

Common representation learning (CRL) learns a shared embedding between t...
research
07/06/2020

Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches

In this work, we evaluate two different image clustering objectives, k-m...
research
12/16/2018

Deep Clustering Based on a Mixture of Autoencoders

In this paper we propose a Deep Autoencoder MIxture Clustering (DAMIC) a...
research
02/24/2023

Permutation-Invariant Set Autoencoders with Fixed-Size Embeddings for Multi-Agent Learning

The problem of permutation-invariant learning over set representations i...
research
01/12/2021

Learning Efficient Representations for Keyword Spotting with Triplet Loss

In the past few years, triplet loss-based metric embeddings have become ...
research
12/07/2020

Joint Optimization of an Autoencoder for Clustering and Embedding

Incorporating k-means-like clustering techniques into (deep) autoencoder...
research
08/01/2022

Backdoor Watermarking Deep Learning Classification Models With Deep Fidelity

Backdoor Watermarking is a promising paradigm to protect the copyright o...

Please sign up or login with your details

Forgot password? Click here to reset