The Group Loss++: A Deeper Look Into Group Loss for Deep Metric Learning
- 31 March 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (2) , 2505-2518
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 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.Keywords
All Related Versions
Funding Information
- Alexander von Humboldt-Stiftung
- Humboldt Research Fellowship
This publication has 84 references indexed in Scilit:
- Unsupervised Learning of Visual Representations Using Videos2015
- FaceNet: A unified embedding for face recognition and clustering2015
- An improved deep learning architecture for person re-identification2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- DeepReID: Deep Filter Pairing Neural Network for Person Re-identification2014
- Mixed Pooling for Convolutional Neural Networks2014
- 3D Object Representations for Fine-Grained Categorization2013
- Graph Transduction as a Noncooperative GameNeural Computation, 2012
- Learning a Similarity Metric Discriminatively, with Application to Face Verification2005
- An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecologyBulletin of the American Mathematical Society, 1967