The Group Loss For Deep Metric Learning

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 sampl

Stats

• citations32
• S2 citations—
• github stars0
• HF likes0
• heat score11.39
• arxiv keyelezi2019the

Related papers

• The Group Loss++: A Deeper Look Into Group Loss For Deep Metric Learning (2022)8.82
• The General Pair-based Weighting Loss For Deep Metric Learning (2019)0.00
• Ensemble Of Loss Functions To Improve Generalizability Of Deep Metric Learning Methods (2021)7.16
• Constellation Loss: Improving The Efficiency Of Deep Metric Learning Loss Functions For Optimal Embedding (2019)0.00
• Deep Metric Learning For Computer Vision: A Brief Overview (2023)6.77
• Learning Intra-batch Connections For Deep Metric Learning (2021)0.00
• Ranked List Loss For Deep Metric Learning (2019)7.50
• Mean Field Theory In Deep Metric Learning (2023)0.00