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

2020-07-06 · Kalun Ho, Janis Keuper, Franz-Josef Pfreundt, Margret Keuper

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 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.

📄 PDF Abstract BibTeX arXiv:2007.03123

Code (0)

등록된 구현이 없습니다.

Tasks

Clusteringimage-classification Image Classification Image ClusteringTriplet

Methods 이 논문이 사용한 방법론

Triplet Loss The goal of Triplet loss, in the context of Siamese Networks, is to maximize the joint probability among all score-pairs i.e. the product of all probabilities. By using its…

k-Means Clustering k-Means Clustering is a clustering algorithm that divides a training set into $k$ different clusters of examples that are near each other. It works by initializing $k$…

Deep Clustering via Center-Oriented Margin Free-Triplet Loss for Skin Lesion Detection in Highly Imbalanced Datasets

2022-04-03 · Saban Ozturk, Tolga Cukur

Melanoma is a fatal skin cancer that is curable and has dramatically increasing survival rate when diagnosed at early stages. Learning-based methods hold significant promise for the detection of melanoma from dermoscopic…

Clustering Deep Clustering Lesion Detection Triplet

Learning Thematic Similarity Metric from Article Sections Using Triplet Networks

2018-07-01 · ACL 2018 7 · Liat Ein Dor, Yosi Mass, Alon Halfon, Elad Venezian 외

In this paper we suggest to leverage the partition of articles into sections, in order to learn thematic similarity metric between sentences. We assume that a sentence is thematically closer to sentences within its secti…

Articles Clustering Collaborative Filtering Document Summarization+6

FaceNet: A Unified Embedding for Face Recognition and Clustering

2015-03-12 · CVPR 2015 6 · Florian Schroff, Dmitry Kalenichenko, James Philbin

Despite significant recent advances in the field of face recognition, implementing face verification and recognition efficiently at scale presents serious challenges to current approaches. In this paper we present a syst…

Clustering Disguised Face Verification Face Identification Face Recognition+2

Vector Embeddings with Subvector Permutation Invariance using a Triplet Enhanced Autoencoder

2020-11-18 · Mark Alan Matties

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 reco…

Clustering Triplet

Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings

2021-01-26 · EACL 2021 2 · Kailash Karthik Saravanakumar, Miguel Ballesteros, Muthu Kumar Chandrasekaran, Kathleen McKeown

We propose a method for online news stream clustering that is a variant of the non-parametric streaming K-means algorithm. Our model uses a combination of sparse and dense document representations, aggregates document-cl…