The Group Loss++: A deeper look into group loss for deep metric learning
- URL: http://arxiv.org/abs/2204.01509v1
- Date: Mon, 4 Apr 2022 14:09:58 GMT
- Title: The Group Loss++: A deeper look into group loss for deep metric learning
- Authors: Ismail Elezi, Jenny Seidenschwarz, Laurin Wagner, Sebastiano Vascon,
Alessandro Torcinovich, Marcello Pelillo, Laura Leal-Taixe
- Abstract summary: Group Loss is a loss function based on a differentiable label-propagation method that enforces embedding similarity across all samples of a group.
We show state-of-the-art results on clustering and image retrieval on four datasets, and present competitive results on two person re-identification datasets.
- Score: 65.19665861268574
- License: http://creativecommons.org/licenses/by/4.0/
- 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.
Related papers
- Data Similarity-Based One-Shot Clustering for Multi-Task Hierarchical Federated Learning [8.37314799155978]
We propose a one-shot clustering algorithm that can effectively identify and group users based on their data similarity.
Our proposed algorithm not only enhances the clustering process, but also overcomes challenges related to privacy concerns, communication overhead, and the need for prior knowledge about learning models or loss function behaviors.
arXiv Detail & Related papers (2024-10-03T17:51:21Z) - A structured regression approach for evaluating model performance across intersectional subgroups [53.91682617836498]
Disaggregated evaluation is a central task in AI fairness assessment, where the goal is to measure an AI system's performance across different subgroups.
We introduce a structured regression approach to disaggregated evaluation that we demonstrate can yield reliable system performance estimates even for very small subgroups.
arXiv Detail & Related papers (2024-01-26T14:21:45Z) - InfoNCE Loss Provably Learns Cluster-Preserving Representations [54.28112623495274]
We show that the representation learned by InfoNCE with a finite number of negative samples is consistent with respect to clusters in the data.
Our main result is to show that the representation learned by InfoNCE with a finite number of negative samples is also consistent with respect to clusters in the data.
arXiv Detail & Related papers (2023-02-15T19:45:35Z) - Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised
Person Re-Identification and Text Authorship Attribution [77.85461690214551]
Learning from fully-unlabeled data is challenging in Multimedia Forensics problems, such as Person Re-Identification and Text Authorship Attribution.
Recent self-supervised learning methods have shown to be effective when dealing with fully-unlabeled data in cases where the underlying classes have significant semantic differences.
We propose a strategy to tackle Person Re-Identification and Text Authorship Attribution by enabling learning from unlabeled data even when samples from different classes are not prominently diverse.
arXiv Detail & Related papers (2022-02-07T13:08:11Z) - Towards Group Robustness in the presence of Partial Group Labels [61.33713547766866]
spurious correlations between input samples and the target labels wrongly direct the neural network predictions.
We propose an algorithm that optimize for the worst-off group assignments from a constraint set.
We show improvements in the minority group's performance while preserving overall aggregate accuracy across groups.
arXiv Detail & Related papers (2022-01-10T22:04:48Z) - Learning Statistical Representation with Joint Deep Embedded Clustering [2.1267423178232407]
StatDEC is an unsupervised framework for joint statistical representation learning and clustering.
Our experiments show that using these representations, one can considerably improve results on imbalanced image clustering across a variety of image datasets.
arXiv Detail & Related papers (2021-09-11T09:26:52Z) - Sum of Ranked Range Loss for Supervised Learning [47.0464265614452]
We introduce the sum of ranked range (SoRR) as a general approach to form learning objectives.
A ranked range is a consecutive sequence of sorted values of a set of real numbers.
We explore two applications in machine learning of the minimization of the SoRR framework, namely the AoRR aggregate loss for binary/multi-class classification at the sample level and the TKML individual loss for multi-label/multi-class classification at the label level.
arXiv Detail & Related papers (2021-06-07T02:11:27Z) - Learning by Minimizing the Sum of Ranked Range [58.24935359348289]
We introduce the sum of ranked range (SoRR) as a general approach to form learning objectives.
A ranked range is a consecutive sequence of sorted values of a set of real numbers.
We explore two applications in machine learning of the minimization of the SoRR framework, namely the AoRR aggregate loss for binary classification and the TKML individual loss for multi-label/multi-class classification.
arXiv Detail & Related papers (2020-10-05T01:58:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.