Laurin Wagner
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Laurin Wagner has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
Alessandro Torcinovich
Ca Foscari University of Venice, Venezia, VE, Italy
1 shared publication- Ismail Elezi
Dynamic Vision and Learning Group, Technical University of Munich, Munich, Germany
1 shared publication - Jenny Seidenschwarz
Dynamic Vision and Learning Group, Technical University of Munich, Mnchen, Germany
1 shared publication - Laura Leal-Taixé
Dynamic Vision and Learning Group, Technical University of Munich, Munich, Germany
1 shared publication Marcello Pelillo
Ca Foscari University of Venice, Venezia, VE, Italy
1 shared publication- Sebastiano Vascon
Department of Environmental Sciences, Informatics and Statistics, Ca' Foscari University of Venice, Venice, Italy
1 shared publication
Latest Publications
- 31 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (2) , 2505-2518
The Group Loss++: A Deeper Look Into Group Loss for Deep Metric Learning
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 state-of-the-art results on clustering and image retrieval on four retrieval datasets, and present competitive results on two person re-identification datasets, providing a unified framework for retrieval and re-identification.
- 31 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (2) , 2505-2518
The Group Loss++: A Deeper Look Into Group Loss for Deep Metric Learning
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 state-of-the-art results on clustering and image retrieval on four retrieval datasets, and present competitive results on two person re-identification datasets, providing a unified framework for retrieval and re-identification.