Hyperbolic Vision Transformers: Combining Improvements in Metric Learning

• URL: http://arxiv.org/abs/2203.10833v2
• Date: Tue, 22 Mar 2022 09:40:22 GMT
• Title: Hyperbolic Vision Transformers: Combining Improvements in Metric Learning
• Authors: Aleksandr Ermolov, Leyla Mirvakhabova, Valentin Khrulkov, Nicu Sebe and Ivan Oseledets
• Abstract summary: We propose a new hyperbolic-based model for metric learning. At the core of our method is a vision transformer with output embeddings mapped to hyperbolic space. We evaluate the proposed model with six different formulations on four datasets.
• Score: 116.13290702262248
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Metric learning aims to learn a highly discriminative model encouraging the embeddings of similar classes to be close in the chosen metrics and pushed apart for dissimilar ones. The common recipe is to use an encoder to extract embeddings and a distance-based loss function to match the representations -- usually, the Euclidean distance is utilized. An emerging interest in learning hyperbolic data embeddings suggests that hyperbolic geometry can be beneficial for natural data. Following this line of work, we propose a new hyperbolic-based model for metric learning. At the core of our method is a vision transformer with output embeddings mapped to hyperbolic space. These embeddings are directly optimized using modified pairwise cross-entropy loss. We evaluate the proposed model with six different formulations on four datasets achieving the new state-of-the-art performance. The source code is available at https://github.com/htdt/hyp_metric.

Related papers

• Optimizing Curvature Learning for Robust Hyperbolic Deep Learning in Computer Vision [3.3964154468907486]
  We introduce an improved schema for popular learning algorithms and a novel normalization approach to constrain embeddings within the variable representative radius of the manifold. Our approach demonstrates consistent performance improvements across both direct classification and hierarchical metric learning tasks while allowing for larger hyperbolic models.
  arXiv  Detail & Related papers  (2024-05-22T20:30:14Z)
• Piecewise-Linear Manifolds for Deep Metric Learning [8.670873561640903]
  Unsupervised deep metric learning focuses on learning a semantic representation space using only unlabeled data. We propose to model the high-dimensional data manifold using a piecewise-linear approximation, with each low-dimensional linear piece approximating the data manifold in a small neighborhood of a point. We empirically show that this similarity estimate correlates better with the ground truth than the similarity estimates of current state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-03-22T06:22:20Z)
• Hyperbolic vs Euclidean Embeddings in Few-Shot Learning: Two Sides of the Same Coin [49.12496652756007]
  We show that the best few-shot results are attained for hyperbolic embeddings at a common hyperbolic radius. In contrast to prior benchmark results, we demonstrate that better performance can be achieved by a fixed-radius encoder equipped with the Euclidean metric.
  arXiv  Detail & Related papers  (2023-09-18T14:51:46Z)
• 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)
• Large-Margin Representation Learning for Texture Classification [67.94823375350433]
  This paper presents a novel approach combining convolutional layers (CLs) and large-margin metric learning for training supervised models on small datasets for texture classification. The experimental results on texture and histopathologic image datasets have shown that the proposed approach achieves competitive accuracy with lower computational cost and faster convergence when compared to equivalent CNNs.
  arXiv  Detail & Related papers  (2022-06-17T04:07:45Z)
• Rethinking Semantic Segmentation: A Prototype View [126.59244185849838]
  We present a nonparametric semantic segmentation model based on non-learnable prototypes. Our framework yields compelling results over several datasets. We expect this work will provoke a rethink of the current de facto semantic segmentation model design.
  arXiv  Detail & Related papers  (2022-03-28T21:15:32Z)
• Adversarial Manifold Matching via Deep Metric Learning for Generative Modeling [5.5840609705075055]
  We propose a manifold matching approach to generative models which includes a distribution generator and a metric generator. The distribution generator aims at generating samples that follow some distribution condensed around the real data manifold. The metric generator utilizes both real data and generated samples to learn a distance metric.
  arXiv  Detail & Related papers  (2021-06-20T23:25:01Z)
• Parametric UMAP embeddings for representation and semi-supervised learning [0.03823356975862005]
  UMAP is a non-parametric graph-based dimensionality reduction algorithm to find low-dimensional embeddings of structured data. We show that Parametric UMAP performs comparably to its non-parametric counterpart while conferring the benefit of a learned parametric mapping. We then explore UMAP as a regularization, constraining the latent distribution of autoencoders, parametrically varying global structure preservation, and improving classifier accuracy for semi-supervised learning.
  arXiv  Detail & Related papers  (2020-09-27T23:45:00Z)
• TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech [63.03318307254081]
  TERA stands for Transformer Representations from Alteration. We use alteration along three axes to pre-train Transformers on a large amount of unlabeled speech. TERA can be used for speech representations extraction or fine-tuning with downstream models.
  arXiv  Detail & Related papers  (2020-07-12T16:19:00Z)

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.