Delaunay Component Analysis for Evaluation of Data Representations

• URL: http://arxiv.org/abs/2202.06866v1
• Date: Mon, 14 Feb 2022 16:48:23 GMT
• Title: Delaunay Component Analysis for Evaluation of Data Representations
• Authors: Petra Poklukar, Vladislav Polianskii, Anastasia Varava, Florian Pokorny, Danica Kragic
• Abstract summary: We introduce Delaunay Component Analysis (DCA) - an evaluation algorithm which approximates the data manifold using a more suitable neighbourhood graph called Delaunay graph. We experimentally validate the proposed DCA method on representations obtained from neural networks trained with contrastive objective, supervised and generative models.
• Score: 20.31649764319578
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Advanced representation learning techniques require reliable and general evaluation methods. Recently, several algorithms based on the common idea of geometric and topological analysis of a manifold approximated from the learned data representations have been proposed. In this work, we introduce Delaunay Component Analysis (DCA) - an evaluation algorithm which approximates the data manifold using a more suitable neighbourhood graph called Delaunay graph. This provides a reliable manifold estimation even for challenging geometric arrangements of representations such as clusters with varying shape and density as well as outliers, which is where existing methods often fail. Furthermore, we exploit the nature of Delaunay graphs and introduce a framework for assessing the quality of individual novel data representations. We experimentally validate the proposed DCA method on representations obtained from neural networks trained with contrastive objective, supervised and generative models, and demonstrate various use cases of our extended single point evaluation framework.

Related papers

• On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning [85.75164588939185]
  We study the discriminative probabilistic modeling problem on a continuous domain for (multimodal) self-supervised representation learning. We conduct generalization error analysis to reveal the limitation of current InfoNCE-based contrastive loss for self-supervised representation learning.
  arXiv  Detail & Related papers  (2024-10-11T18:02:46Z)
• (Deep) Generative Geodesics [57.635187092922976]
  We introduce a newian metric to assess the similarity between any two data points. Our metric leads to the conceptual definition of generative distances and generative geodesics. Their approximations are proven to converge to their true values under mild conditions.
  arXiv  Detail & Related papers  (2024-07-15T21:14:02Z)
• COBRA -- COnfidence score Based on shape Regression Analysis for method-independent quality assessment of object pose estimation from single images [1.6249398255272316]
  We present a generic algorithm for scoring pose estimation methods that rely on single image semantic analysis. The algorithm employs a lightweight putative shape representation using a combination of multiple Gaussian Processes. Our confidence measure comprises the average mixture probability of pixel back-projections onto the shape template.
  arXiv  Detail & Related papers  (2024-04-25T09:55:35Z)
• Unified Multi-View Orthonormal Non-Negative Graph Based Clustering Framework [74.25493157757943]
  We formulate a novel clustering model, which exploits the non-negative feature property and incorporates the multi-view information into a unified joint learning framework. We also explore, for the first time, the multi-model non-negative graph-based approach to clustering data based on deep features.
  arXiv  Detail & Related papers  (2022-11-03T08:18:27Z)
• A Spectral Method for Assessing and Combining Multiple Data Visualizations [13.193958370464683]
  We propose an efficient spectral method for assessing and combining multiple visualizations of a given dataset. The proposed method provides a quantitative measure -- the visualization eigenscore -- of the relative performance of the visualizations for preserving the structure around each data point. We analyze multiple simulated and real-world datasets to demonstrate the effectiveness of the eigenscores for evaluating visualizations and the superiority of the proposed consensus visualization.
  arXiv  Detail & Related papers  (2022-10-25T02:13:19Z)
• Probabilistic methods for approximate archetypal analysis [8.829245587252435]
  Archetypal analysis is an unsupervised learning method for exploratory data analysis. We introduce two preprocessing techniques to reduce the dimension and representation cardinality of the data. We demonstrate the usefulness of our results by applying our method to summarize several moderately large-scale datasets.
  arXiv  Detail & Related papers  (2021-08-12T14:27:11Z)
• GeomCA: Geometric Evaluation of Data Representations [21.83249229426828]
  We present Geometric Component Analysis (GeomCA) algorithm that evaluates representation spaces based on their geometric and topological properties. We demonstrate its applicability by analyzing representations obtained from a variety of scenarios, such as contrastive learning models, generative models and supervised learning models.
  arXiv  Detail & Related papers  (2021-05-26T11:41:40Z)
• Deep Dimension Reduction for Supervised Representation Learning [51.10448064423656]
  We propose a deep dimension reduction approach to learning representations with essential characteristics. The proposed approach is a nonparametric generalization of the sufficient dimension reduction method. We show that the estimated deep nonparametric representation is consistent in the sense that its excess risk converges to zero.
  arXiv  Detail & Related papers  (2020-06-10T14:47:43Z)
• Evaluating the Disentanglement of Deep Generative Models through Manifold Topology [66.06153115971732]
  We present a method for quantifying disentanglement that only uses the generative model. We empirically evaluate several state-of-the-art models across multiple datasets.
  arXiv  Detail & Related papers  (2020-06-05T20:54:11Z)
• CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus [62.86856923633923]
  We present a robust estimator for fitting multiple parametric models of the same form to noisy measurements. In contrast to previous works, which resorted to hand-crafted search strategies for multiple model detection, we learn the search strategy from data. For self-supervised learning of the search, we evaluate the proposed algorithm on multi-homography estimation and demonstrate an accuracy that is superior to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-01-08T17:37:01Z)

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.