Volltext-Downloads (blau) und Frontdoor-Views (grau)
The search result changed since you submitted your search request. Documents might be displayed in a different sort order.
  • search hit 2 of 647
Back to Result List

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

  • In this work, we evaluate two different image clustering objectives, k-means clustering and correlation clustering, in the context of Triplet Loss induced feature space embeddings. Specifically, we train a convolutional neural network to learn discriminative features by optimizing two popular versions of the Triplet Loss in order to study their clustering properties under the assumption of noisyIn this work, we evaluate two different image clustering objectives, k-means clustering and correlation clustering, in the context of Triplet Loss induced feature space embeddings. Specifically, we train a convolutional neural network to learn discriminative features by optimizing two popular versions of the Triplet Loss in order to study their clustering properties under the assumption of noisy labels. Additionally, we propose a new, simple Triplet Loss formulation, which shows desirable properties with respect to formal clustering objectives and outperforms the existing methods. We evaluate all three Triplet loss formulations for K-means and correlation clustering on the CIFAR-10 image classification dataset.show moreshow less

Export metadata

Additional Services

Share in Twitter Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author:Kalun Ho, Janis KeuperORCiDGND, Franz-Josef Pfreundt, Margret Keuper
Date of Publication (online):2020/07/06
Pagenumber:8
Language:English
Document Type:Conference Proceeding
Open Access:Frei zugänglich
Institutes:Bibliografie
Release Date:2021/02/10
Licence (German):License LogoEs gilt das UrhG
Note:
Conference: accepted at ICPR 2021. At: Milano
URL:https://www.researchgate.net/publication/342832627_Learning_Embeddings_for_Image_Clustering_An_Empirical_Study_of_Triplet_Loss_Approaches
ArXiv Id:http://arxiv.org/abs/2007.03123