The group loss++: A deeper look into group loss for deep metric learning

Ismail Elezi, Jenny Seidenschwarz, Laurin Wagner, Sebastiano Vascon, Alessandro Torcinovich, Marcello Pelillo, Laura Leal-Taixé

Abstract:

Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural
networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes. Much research
has been devoted to the design of smart loss functions or data mining strategies for training such networks. Most methods consider
only pairs or triplets of samples within a mini-batch to compute the loss function, which is commonly based on the distance between
embeddings. We propose Group Loss, a loss function based on a differentiable label-propagation method that enforces embedding
similarity across all samples of a group while promoting, at the same time, low-density regions amongst data points belonging to
different groups. Guided by the smoothness assumption that “similar objects should belong to the same group”, the proposed loss
trains the neural network for a classification task, enforcing a consistent labelling amongst samples within a class. We design a set of
inference strategies tailored towards our algorithm, named Group Loss++ that further improve the results of our model. We show stateof-the-art results on clustering and image retrieval on four retrieval datasets, and present competitive results on two person reidentification datasets, providing a unified framework for retrieval and re-identification.