Rethinking preventing class-collapsing in metric learning with margin-based losses

• URL: http://arxiv.org/abs/2006.05162v2
• Date: Fri, 27 Aug 2021 14:13:34 GMT
• Title: Rethinking preventing class-collapsing in metric learning with margin-based losses
• Authors: Elad Levi, Tete Xiao, Xiaolong Wang, Trevor Darrell
• Abstract summary: Metric learning seeks embeddings where visually similar instances are close and dissimilar instances are apart. margin-based losses tend to project all samples of a class onto a single point in the embedding space. We propose a simple modification to the embedding losses such that each sample selects its nearest same-class counterpart in a batch.
• Score: 81.22825616879936
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Metric learning seeks perceptual embeddings where visually similar instances are close and dissimilar instances are apart, but learned representations can be sub-optimal when the distribution of intra-class samples is diverse and distinct sub-clusters are present. Although theoretically with optimal assumptions, margin-based losses such as the triplet loss and margin loss have a diverse family of solutions. We theoretically prove and empirically show that under reasonable noise assumptions, margin-based losses tend to project all samples of a class with various modes onto a single point in the embedding space, resulting in a class collapse that usually renders the space ill-sorted for classification or retrieval. To address this problem, we propose a simple modification to the embedding losses such that each sample selects its nearest same-class counterpart in a batch as the positive element in the tuple. This allows for the presence of multiple sub-clusters within each class. The adaptation can be integrated into a wide range of metric learning losses. The proposed sampling method demonstrates clear benefits on various fine-grained image retrieval datasets over a variety of existing losses; qualitative retrieval results show that samples with similar visual patterns are indeed closer in the embedding space.

Related papers

• Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning [59.44422468242455]
  We propose a novel method dubbed ShrinkMatch to learn uncertain samples. For each uncertain sample, it adaptively seeks a shrunk class space, which merely contains the original top-1 class. We then impose a consistency regularization between a pair of strongly and weakly augmented samples in the shrunk space to strive for discriminative representations.
  arXiv  Detail & Related papers  (2023-08-13T14:05:24Z)
• Deep Metric Learning Assisted by Intra-variance in A Semi-supervised View of Learning [0.0]
  Deep metric learning aims to construct an embedding space where samples of the same class are close to each other, while samples of different classes are far away from each other. This paper designs a self-supervised generative assisted ranking framework that provides a semi-supervised view of intra-class variance learning scheme for typical supervised deep metric learning.
  arXiv  Detail & Related papers  (2023-04-21T13:30:32Z)
• Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning [99.14132861655223]
  We propose a novel intra-class adaptive augmentation (IAA) framework for deep metric learning. We reasonably estimate intra-class variations for every class and generate adaptive synthetic samples to support hard samples mining. Our method significantly improves and outperforms the state-of-the-art methods on retrieval performances by 3%-6%.
  arXiv  Detail & Related papers  (2022-11-29T14:52:38Z)
• The Group Loss++: A deeper look into group loss for deep metric learning [65.19665861268574]
  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.
  arXiv  Detail & Related papers  (2022-04-04T14:09:58Z)
• Boosting few-shot classification with view-learnable contrastive learning [19.801016732390064]
  We introduce contrastive loss into few-shot classification for learning latent fine-grained structure in the embedding space. We develop a learning-to-learn algorithm to automatically generate different views of the same image.
  arXiv  Detail & Related papers  (2021-07-20T03:13:33Z)
• MSE Loss with Outlying Label for Imbalanced Classification [10.305130700118399]
  We propose mean squared error (MSE) loss with outlying label for class imbalanced classification. MSE loss is possible to equalize the number of back propagation for all classes and to learn the feature space considering the relationships between classes as metric learning. It is possible to create the feature space for separating high-difficulty classes and low-difficulty classes.
  arXiv  Detail & Related papers  (2021-07-06T05:17:00Z)
• Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning [49.04790688256481]
  The goal of generalized zero-shot learning (GZSL) is to recognise both seen and unseen classes. Most GZSL methods typically learn to synthesise visual representations from semantic information on the unseen classes. We propose a novel framework that leverages dual variational autoencoders with a triplet loss to learn discriminative latent features.
  arXiv  Detail & Related papers  (2021-01-09T05:21:27Z)
• Unsupervised Representation Learning by InvariancePropagation [34.53866045440319]
  In this paper, we propose Invariance propagation to focus on learning representations invariant to category-level variations. With a ResNet-50 as the backbone, our method achieves 71.3% top-1 accuracy on ImageNet linear classification and 78.2% top-5 accuracy fine-tuning on only 1% labels. We also achieve state-of-the-art performance on other downstream tasks, including linear classification on Places205 and Pascal VOC, and transfer learning on small scale datasets.
  arXiv  Detail & Related papers  (2020-10-07T13:00:33Z)
• 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.