TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Ho, Kalun
A1  - Keuper, Janis
A1  - Pfreundt, Franz-Josef
A1  - Keuper, Margret
T1  - Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches
N2  - 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.
Y1  - 2020
AX  - 2007.03123
N1  - Preprint; Conference: accepted at ICPR 2021 (Milano)
SP  - 8
S1  - 8
ER  -